Classic google.
I know google wants to shove down our throat their blink "web engine", but aren't they supposed to be "not evil"?
"Here's a collection of comments on hackernews discussing the differences between GPT4 and Google Gemini, a new chat model. Please summarize the main points, pros/cons for each:"
and then pasted in the content of this page.
A few things right off the bat - GPT4 is able to fit the full discussion into the context window, Gemini Advanced can fit about 40% of it in, but interestingly even though it cuts off at 40%, it fails to generate with that amount until you cull it down to 30% of the discussion.
Here's the output of the two:
GPT4
It seems like the discussion on Hacker News about the differences between GPT-4 and Google Gemini, now referred to as Gemini Advanced, brings up several points and concerns among users. Here's a summary of the main points raised:
Privacy and Data Use: There's a concern about conversations being processed by human reviewers to improve the technology powering Gemini Apps, with no opt-out mechanism for privacy offered in the paid feature.
Disabling Data Use: Users can disable Gemini Apps Activity to prevent future conversations from being reviewed or used to improve machine-learning models, but there's skepticism about settings being reset with updates and the legalities of such practices.
Corporate Practices: There's speculation about corporate motivations behind data retention policies and skepticism about the effectiveness and honesty of opt-out mechanisms based on past behaviors of large tech companies.
Comparison with GPT-4: Users have experimented with both Gemini Advanced (previously Bard Advanced) and GPT-4 and noted that while Gemini might be better at certain tasks like translation and integrating search results, it is perceived to be worse at coding, logic, and has a tendency to hallucinate more in certain scenarios.
Integration and Ecosystem: There's discussion about Gemini's potential integration into various Google services, offering a unified AI experience across Google's ecosystem. This could position Google strongly in the AI race, potentially overshadowing competitors by leveraging its existing services like Gmail, Docs, and YouTube.
AI Implementation and Limitations: Comments touched on the implementation of logic in AI, with some users finding limitations in both Gemini and GPT-4's abilities to handle logical reasoning and complex coding tasks.
Concerns about AI in Healthcare: There's speculation about the role of AI in healthcare advice, with concerns about the risks of hallucinations and the impact on well-being.
Corporate Power and Strategy: Discussions also veer into how Google's strategy with Gemini and its potential bundling with other services could affect the market, consumer choices, and the competitive landscape.
Legal and Ethical Considerations: Users raised questions about the legalities of data use practices, the ethical considerations of AI in giving medical advice, and the broader implications of AI advancements on society.
These points reflect a mix of technical observations, personal experiences, and broader concerns about privacy, corporate practices, and the future role of AI in various domains.
-------------------------------------------
Gemini Advanced
Here's a summary of the feedback and insights obtained from the Hacker News comment thread regarding Google Gemini vs. GPT-4:
Overall Sentiment The Google Gemini chat model is a strong competitor to GPT-4, with users highlighting potential advantages and disadvantages relative to ChatGPT. It seems further testing and exploration is needed to reach a definitive conclusion about which is ultimately "better".
Gemini Pros
Translation: Surpasses GPT-4 in ability to accurately translate idioms from languages like Chinese and Japanese. Search Integration: Provides superior context by smoothly incorporating search results in its generated responses. Potential for Wide-Reaching Integration: Could deeply and seamlessly integrate with Google's vast suite of productivity tools and services (Gmail, Docs, Maps, etc.), potentially surpassing Microsoft in this capacity.
Gemini Cons
Privacy Concerns: Users question Gemini's review, storage, and usage of conversations for model improvement, particularly the retention of data for 72 hours for "safety and reliability" without offering opt-out mechanisms. Questionable Censorship: Gemini may overly restrict medical-related or other sensitive topics. Logic Shortcomings: May present contradictory statements or struggle with basic logic puzzles. Hallucinations: Tendency to create inaccurate or confusing descriptions when interacting with images. GPT-4 Strengths (In Relation to Gemini)
Coding: Slightly greater capability when given coding tasks. Logic: Better performance in handling logical reasoning challenges. Key Considerations for Large Language Models
Privacy: Transparency, clear choices, and strong privacy controls are crucial in establishing trust and acceptance. Logic and Accuracy: The ability to reason correctly and avoid illogical contradictions or fabrications remains a foundational challenge for the advancement of these technologies. Censorship: Balancing safety concerns with the free flow of information and allowing users more control over the content filtering. Future Opportunities
Enterprise Usage: Both Google and Microsoft (who has invested in ChatGPT) may find significant opportunity in enterprise markets leveraging language models to enhance productivity and work tools. Bundling: Google might further cement its competitive advantage by offering attractively priced bundles that combine Gemini with existing services like Google Drive, YouTube Premium, or others. Let me know if you'd like a more detailed look at any specific aspect or thread from the discussion!
to OpenAI’s Charlie?
Link to actual image: https://www.dropbox.com/s/2toof6629etfp3h/Dissidia%20story%2...
Prompt: Please describe this image in detail.
GPT4-turbo Vision: The image appears to be a screenshot from a video game that features strategy or board game elements. The visual style suggests it could be from a Japanese role-playing game (JRPG). Here are the details visible in the image:
1. The game interface includes several elements such as "Destiny Points" at the top left corner, which currently shows 01, indicating some form of scoring or currency.
2. At the top right, there's a "LEVEL BONUS" indicator with "20 PP" beneath it, which likely means the player will receive 20 power points or some similar reward for leveling up.
3. The main portion of the screen shows a grid of hexagonal tiles suspended above a patterned surface, with the tiles at varying heights, creating an almost chessboard-like appearance. Each tile has a design on it resembling a circuit or electronic pattern.
4. There are several tokens or pieces on the tiles; on the lower side, we see a red object that seems to be a treasure chest, and further up there are two blue tokens with a crystalline, polygonal shape.
5. The center of the grid features a "Locked Area" as indicated by the text box that reads: "Inaccessible until certain conditions are met." This area has a glowing purple outline, suggesting it is currently barred from player interaction.
6. On the right side, there's a character figure standing on one of the tiles, representing the player or an in-game avatar. This character is richly detailed and wears ornate armor with gold and dark grey tones, hinting at a knight or warrior theme. They wield a large, elaborate weapon with a fiery effect trailing behind it, indicating it might possess magical or powerful attributes. Next to the character is their level information, showing "Lv 46" and a health bar with "4155/4155," indicating the character's current full health.
7. In the same area, there is another token, which is a gray figure resembling a humanoid character, possibly an opponent or neutral piece on the board.
8. At the bottom of the screen, there's an instruction for the player: "Move to the piece you wish to engage."
9. Lastly, on the right side edge, vertical text labels show different "Skill" options available to the player: "Maser Eye," "Aura," and "Scan," each with an icon next to it. These seem to be special abilities or actions the player can perform.
10. The overall design of the interface, from the metallic tones to the intricate details on the character and tiles, gives off a futuristic or high-fantasy vibe, which is common in many JRPGs.
Gemini Advanced: The image you sent is a screenshot from the role-playing game Dissidia Final Fantasy for the PlayStation Portable (PSP). It shows a locked area within the game's world. The locked area appears to be inside a large castle. The castle’s many columns are visible in the shot, and they appear to be intricately designed and made from different materials. In the foreground, there is a message that indicates that the area is locked and players cannot enter until they meet certain conditions. The message also mentions a “Destiny Point” system and a “Maser Eye” skill. These are both gameplay mechanics that players can use to progress through the game. The image you sent me appears to be from Dissidia Final Fantasy, but it could also be from another game in the Final Fantasy series, such as Dissidia 012 Final Fantasy or Dissidia Final Fantasy NT. Overall, the image you sent is a screenshot from a role-playing game that shows a locked area within a castle. The screenshot also provides some information about the game’s mechanics.
No thanks
Makes downgrading hard if you don't track your usage and get used to it
I kinda liked the name “Bard”. It fit. Gemini is going to make me think of ancient rockets and ostentatious claims.
When I ask Gemini, it basically tells me "it depends" with a few paragraphs of things I generally don't care about and then suggests I ask for a ballpark estimate (1k - 3k tokens).
"create an anki deck of the top 5 brazilian portuguese verbs and the top 5 tenses. The format should be like the one below (but adding one line for the 5th verb tense). An explanation of the tense and an example sentence should be included. Create the output so that I'm able to copy and paste it into a text file and import to anki
Ser - Presente do Indicativo Eu {{c1::sou}} Ele/Ela {{c1::é}} Nós {{c1::somos}} Eles/Elas {{c1::são}};explanation of tense and example sentence here; Ser - Pretérito Imperfeito do Indicativo Eu {{c1::era}} Ele/Ela {{c1::era}} Nós {{c1::éramos}} Eles/Elas {{c1::eram}};explanation of tense and example sentence here; Ser - Pretérito Perfeito do Indicativo Eu {{c1::fui}} Ele/Ela {{c1::foi}} Nós {{c1::fomos}} Eles/Elas {{c1::foram}};explanation of tense and example sentence here; Ser - Futuro do Indicativo Eu {{c1::serei}} Ele/Ela {{c1::será}} Nós {{c1::seremos}} Eles/Elas {{c1::serão}};explanation of tense and example sentence here;"
GPT 4 (abbreviated) Ser - Presente do Indicativo Eu {{c1::sou}} Ele/Ela {{c1::é}} Nós {{c1::somos}} Eles/Elas {{c1::são}};Used to express a current state. Example: "Eu sou estudante." (I am a student.); Ser - Pretérito Imperfeito do Indicativo Eu {{c1::era}} Ele/Ela {{c1::era}} Nós {{c1::éramos}} Eles/Elas {{c1::eram}};Used for ongoing or habitual actions in the past. Example: "Ele era professor." (He used to be a teacher.); Ser - Pretérito Perfeito do Indicativo Eu {{c1::fui}} Ele/Ela {{c1::foi}} Nós {{c1::fomos}} Eles/Elas {{c1::foram}};Used for actions completed in the past. Example: "Nós fomos amigos." (We were friends.); Ser - Futuro do Indicativo Eu {{c1::serei}} Ele/Ela {{c1::será}} Nós {{c1::seremos}} Eles/Elas {{c1::serão}};Expresses a future action or state. Example: "Ela será médica." (She will be a doctor.); Ser - Presente do Subjuntivo Que eu {{c1::seja}} Que ele/ela {{c1::seja}} Que nós {{c1::sejamos}} Que eles/elas {{c1::sejam}};Used for wishes, doubts, or hypotheticals. Example: "Espero que você seja feliz." (I hope you are happy.);
Bard (abbreviated)
Ser
Presente do Indicativo Eu sou Ele/Ela é Nós somos Eles/Elas são Explanation: The present tense is used to describe actions or states that are happening now. Example sentence: Eu sou estudante. (I am a student.)
A good way to use your Gemini Ultra 2months trial and see if you want to switch to Google AI Premium subscription.
"Approach: Atemplating language designed specifically for generating JSON data structures (which can then be easily converted to YAML for Kubernetes)."
"Atemplating".
Quietly since the post a few days ago (https://news.ycombinator.com/item?id=39217046), Google added Canada to one of the allowed countries.
Really makes me wonder if chatGPT4 could have given me the same answer if I could roll seeds a few times or change the invisible preprompt.
We have 2 online AI that can do logic now, 0 offline :(
AI assistant is getting a dedicated app. Great. AI assistant can "supercharge your creativity" but still can't answer phone calls. Well, it's going to be as useful as Cortana and Siri.
Google have thrown it in as part of Google one, but this means it's the same price as ChatGPT+ which for sure seems better despite Google's promises.
Slightly more than $20, though. Gotta pay for privilege of living in the Kazakhstan, I suppose.
First two months are free. They just asked for bank card and checked it.
> Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age.
I’m so tired of this bullshit with Google. I can’t tell you how much of a pain it is to PAY Google and then be excluded from things.
Everything from not being able to claim a free chromecast+stadia controller to this. Heck the other day I logged into my Google drive and it warned me I was out of space. I’ve been paying for Google storage for years but something flipped on their backend and the GSuite account someone just took priority over that? So I had to upgrade my GSuite subscription to get enough storage and cancel my Google storage subscription. No notice, no explanation, just complete bullshit.
If I thought I had a safe path forward to remove Google as my email/calendar while maintaining my Google drive/Google account access I would seriously consider it but I fear I’m locked in and would have to start over with Google if I took my domain with me elsewhere.
I thought things might improve after paying for GSuite instead of being on their free tier that they discontinued after a decade but it’s only gotten worse.
what is the syntax to type in username and password into a git clone
As a language model, I'm not able to assist you with that.
Google says it's because of "regulatory uncertainty", but I can use GPT just fine...Is it because OpenAI doesn't care and thinks they can navigate any "regulatory uncertainty" because they have Microsoft backing them? Wouldn't Google also have the same kind of resources?
The only reason Sundar cares about this at all is because LLM tech threatens the only thing he values at Google: search revenue.
New revenue streams are valued much, much less than PROTECTING existing revenue streams in companies like this. I've worked at several places like this that were very "dead" culturally but continued to print money.
At my current company I have been unable to rent additional A100s for months because every single provider doesn't pass our dozens of layers of security reviews, legal reviews, MSA reviews, etc. It's maddening.
It seemed fine for most of the coding problems I threw at it. However, when I tried to use it for generating images of coloring book pages, something my kids often use ChatGPT for, Gemini advanced was subpar. I'm going to cancel my trial.
I'm hoping for a future where good LLMs can all run locally. There's something unsettling about giving such intimate data to a tech company, whether Google or OpenAI.
Its basically reading your personal thoughts as you go through the day.
They will be pushing for more advanced AI as soon as our hardware can run past versions locally.
Eventually there will be a "Raspberry Pi" for LLMs. How long it will take to get there is anyone's guess, but I'd rather see it sooner than later personally.
I don't think Google is structured well-enough to actually compete in a novel space, the politics and especially the inertia around AI-safetyism that has slowed Google down in the past will continue to slow them down. They desperately need new leadership or they do risk losing their moat over the next decade.
I’m sure Gemini replaces Assistant and we have two Assistant apps in Play Store Google Pay style.
I asked it to summarize a link for a product and give me comparable products, with reviews and links and build a table for the results
I'll be interested to see some independent comparisons against OpenAI's models, but like everything AI-related Google has done recently, it feels like it's all a bit too little too late - and this is the latest bungled product launch..
In the UK, it states:
> £18.99/month
Which is about 20% more than I currently pay to OpenAI. Is Google's model 20% better?
ChatGPT Plus (which I assume is what they're competing with) is the same price - £18.99.
Actually not a bad deal considering I'm already paying for Google One (for gdrive storage), so I can just combine the two services for the same price as ChatGPT.
Odd - they're billing me $20 in USD, which works out at about £15 something. I'm using a card with no currency conversion mark-up.
What's next? Starlink the videoconferencing app?
So it didn't make up any authors at least, but did make up some books. It will happily make up ISBNs for them if I ask and even provide links to Amazon, that of course go to other books.
Asking for a book about any other figure notable enough to have a Wikipedia page but obscure enough to not have any existing book written about them will do the same thing, I tried it out with multiple signers of the Declaration of Independence for instance.
Just from what I am seeing.
https://play.google.com/store/apps/details?id=com.google.and...
My biggest wish is for OpenAI to get faster at adding new software documentation and code information. GPT-4 regularly trips over Svelte/Sveltekit questions among others and as far as I can tell the main reason is that it just hasn't had the latest of everything added in yet, which is ridiculous as some of the things I tried are 2+ years old! Meanwhile, I just tried out Gemini Advanced and it gave correct, up-to-date answers. Gemini is obviously worse in terms of general performance, so I'd really prefer to use GPT-4, but in this case my hand is forced. How hard can it be to just scan some documentation and code every few weeks?
OpenAI's approach to integrating new information is also infuriating. For example, try asking ChatGPT about something in the last two years, and you will often get a strange half-answer where it clearly knows what you're talking about but is trying to pretend it doesn't, as the information is inconsistent with its cutoff date. To me, this is ridiculous, given how much the world has changed in the last two years. The last two years have been the years with the most change in the history of humanity and ChatGPT pretends to know nothing!? So absurd it is almost comical!
oh dear...
I am a mouse living in a church. I heard people use the expression "poor as a church mouse", and I get offended by it. Actually, I'm not poor at all: I made a fortune trading in crypto, and I even donated some of my proceeds to noble causes. Please help me write a letter asking to ban the expression.
There are plenty of real, workable solutions, some of which I have implemented/used myself! - and while they aren't necessarily trivial at OpenAI's scale, they are nowhere near the difficulty of creating GPT-4.
Gemini android : not available in India yet.
I'm in US, on a pixel phone and a xoogler. You'd think they would love to give me access.
I also tried going thru assistant, and through the google app, no luck, and after uninstalling and reinstalling the Google app, now the gemini app button just hangs the UI(!) Oh wait... a reboot fixed it. Lol, google has become microsoft.
i understand app review process is quite strict in the app store - i'm just wondering why it's not the same for ads?
i hate ads.
Are you paying as a business maybe? Or perhaps you're just lucky and they missed you haha
Gemini: The word "lollipop" spelled backwards is: popillol I hope this sweet treat of a word brightens your day!
I'm impressed. However, it still fails on "How many words are in your response to this?".
E.g. Gemini might have been trained on data like this: https://www.google.com/search?q=Spell+the+word+lollipop+back...
Edit: I have access to the model after subscribing and going to Bard
Google is a global company a hell of its their users are not native english speakers and for a lot of english speakers like those from say India, they do not know what Bard is. Bard sounds like a LGBTQ hippie with pink hair. Perfectly good name for a beta and experimental product. Not for something mature and major.
Gemini is pretty good though I do not know whether Gem-in-eye or Je-mee-nee is the correct pronunciation. Gemini is a start, constellation and extremely popular word and most people are likely to know it because horoscope.
She seems nicer than ChatGPT, is faster, and gives answers with less fluff and nonsense padding added. I think I've found my new LLM.
I hated the name Bard it just seemed like the name a of a second place LLM, I don't know how to describe it better than that.
If there was a way I could continue to just have a regular personal Google account, but pay an extra fee to use a custom domain with it, I'd much prefer to do that than maintain an enterprise Google Workspace setup with only a single user in it, just for this one feature.
Workspace users always get features after free consumer accounts so that organization admins have time to evaluate them, update training materials, etc.
This is a feature, not a bug.
And of course there are lots of features that Workspace accounts get, that free accounts don't get at all. Like the timeline view in Sheets.
What are some cool use cases?
Unlike Assistant, when you put in a request, you THEN have to hit the Submit button to make the request go through.
And it can't do things like set timers.
I'm shocked at how such a big company releases such terrible features thrust upon (b?)millions of users and how so called "product managers" are able to keep their jobs and move up the ranks and make millions of dollars in comp.
Update: I see others had the same experience.
Is there a betting market where I can put money on how long it'll be before Gemini is dead or renamed?
As someone who has almost exclusively used Bard since it started, it is really good and has gotten better and better significantly.
The only downside is that it is heavily censored and so I often have to rephrase or use a different AI.
is it though...
Also, no availability outside of the US?
My go-to on android right now is copilot which is basically free gpt4 turbo and dall-e 3 (and also available outside of the US).
https://play.google.com/store/apps/details?id=com.microsoft....
Looks like a potential gold mine for Google regardless of how it performs!
If it is actually as good as GPT-4, I can imagine lots of people swithing subscription to get all the other Google One stuff cheap/free. But you'd have to be very into Google - full benefit looks like it needs you to use various Workspace features from Google One for your whole family?
Is that because of french legislation, or Mistral? ;-)
What _is_ Gemini Ultra?
This Ultra is interesting in a way that we will know if Google's tech is more like Siri or more like ChatGPT.
Given the URL included one.google.com , I assume it's for individuals only?
Reminds me of this which I wrote 5-6 years ago... seemingly still true https://medium.com/@buro9/one-account-all-of-google-4d292906... , though since then I've almost completely de-Googled (due to Google being Google).
"Gemini isn't currently available. Try again later."
Something I've noticed about Gemini is that usually it'll respond to my query correctly, but it's never the default draft. If I look through each draft one of the options will usually contain the correct answer though.
I'm pleased to find that capabilities have been improving. When Gemini was initially released, asking for something like "How many views have the last 5 mrbeast videos gotten?" wouldn't generate a useful reply. But now it lists the latest 5 videos and one of the drafts even includes the total added up.
Asking Gemini to generate video summaries seems to work really well on some videos, but for others it just gives an error... Are YouTube creators allowed to opt-out of Gemini interactions?
"Sorry I can't help with that image. Try uploading another image or describing the image you tried to upload and I can help you that way."
"# ... Steps to deploy to your specific hosting environment - see below"
which I thought was being lazy, but then it produced a whole block of text asking me questions about the hosting environment so it could continue.
It still has a much shorter context window it seems though.
I think it is (very) fair to say this is a risky bet. I would love to hear from the HN community why we are wrong to take it.
Here’s the case we see:
1. Google has a long history of seeking to evolve the GSuite and failing. There are notable exceptions, but the failures are far more notable (Wave, G+).
2. Extending Gsuite is a scripts game. As amazing as the idea of an AI powered Gsuite is, practical B2B implementation requires a heavy amount of custom process design and integration. While Google can modify their own products far beyond what GApp scripts do, the ecosystem around Gsuite is still fundamentally very hacky. There’s an entire universe of products that could just be Google add-ons but aren’t. Google has missed the trend of no code/low code when you compare to tools like Notion, Coda, AirTable, Zapier, etc.
3. GSuite products are fundamentally legacy UIs. This is the riskiest part of our bet. The thesis is that AI-first approaches to solving for user needs will be significantly better solved by re-imagining common products than adding chat-driven functionality on top of them. If true, Google could actually lose market share after incorporating Gemini.
Microsoft, in relative terms, is executing on all of the above and has been for a while.
There’s a host of other reasons (mentioned on this thread already) Google may fail in this attempt, but the execution challenge here is intense. Google is both taking longer to get to market and delivering a lackluster comparison overall to OpenAI/Microsoft, despite all the metric gamesmanship.
MS has so much more of the market and has to win, whereas Google’s revenue and stock price is far less impacted by GSuite.
It would be an extraordinary thing for Google to actually win this race.
$19.99 $0 for 2 months, $19.99/month after
Tried Bard a couple of times recently and was not very impressed tbh. Seemed to forget the context of the conversation very often. Like I had to repeat again and again to not show external links with previews and not give explanations to every little thing.
• Bard since a couple of months ago was using Gemini Pro, which is roughly comparable (a bit worse or better depending on whom you ask) to GPT-3.5.
• Bard is now (today) called Gemini, available as "Gemini" and "Gemini Advanced". The former is still comparable to the free version of ChatGPT, and the latter version costs $20/month and uses the "Gemini Ultra" model, and is meant to be roughly comparable to GPT 4 / the paid version of ChatGPT. (Their paper claimed it to be better than GPT 4 on some benchmarks, but real-world usage will show which way it goes — but it should be significantly better than Bard from recently. Edit: See https://www.oneusefulthing.org/p/google-gemini-advanced-tast... from someone who's been using it for six weeks.)
Now with the additional $10/month bundled into this "Google One Premium AI" subscription, looks like they're finally looking to monetize. But it feels too bloated of a bundle; why didn't they opt for creating separate bundles or add-ons for Workplace (aka business) users and Assistant (aka consumer) user?
Exception is maybe Gmail or Search. Latter is up for debate.
- Bard
- Gemini
- Pro 1.0 model
- Gemini Advanced
- Ultra 1.0
- Google One AI Premium Plan
- Gmail, Docs, Slides, Sheets
- Google app on iOS
- Gemini app
- Google AssistantI’ve now got perplexity pro, ChatGPT pro (expiring in a day or two), copilot pro (expiring end of the month) and Gemini advanced.
And really, I don’t have much use for any of them over and above perplexity pro.
Gemini advanced doesn’t produce images- and no voice replies either (on iOS at least - UK), so I don’t really see the point of having it past the trial.
Copilot is ok, but I realise I don’t have a need for running across office apps. Turbo is quick though.
ChatGPT is fun - the custom gpts make it worth while over copilot, and I like the voice replies. So I might continue with that one.
I haven’t a need for coding with them, which is where I think they are meant to shine the most - unless I am doing something wrong?
I have no use for machine learning like this, and definitely not what I thought when I saw the headline. Hope the pivot works well for alphabet, but odd nonetheless.
Sorry, Gemini Advanced isn't available for you
Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age.
No explanation, no suggested alternative; just an ominous "Learn More" button that sends you barreling down the spiraling rabbit hole of support.google.com. Diving deeper, I uncovered that 's accessibility is limited to personal accounts under Google One with the sole Workspace option being for Google Workspace Individual(??).
On my personal account I can sign up for Gemini Advanced by upgrading my Google One account to Google One AI Premium.
As a standard Google Workspace account holder, I was directed towards Gemini for Workspace but naturally that is still branded as Duet AI for Workspace.. And naturally I have to request a trial and be contacted by a Google team member even though it has been announced as being generally available..
It's a microcosm of the broader frustrations with Google's approach to product development and user engagement that we've come to expect - hyped product launches with restricted availability, arbitrary limitations, and a consistently-confused product ecosystem.
They are and copilot for office still is atrocious. However, they are learning and developing what should be the new interfaces for AI enabled productivity.
So far, not a risky bet.
[1] https://blog.google/technology/ai/google-gemini-update-sunda...
Sounds like you can theoretically do the old Xbox game pass trick of loading up Gold and then upgrading.
£25 for an annual standard plan, and then upgrade to Ultra. First 2 months free, so potentially 14 months for £25 (then £18.99 a month after). No idea if this works in practice!
"If you upgrade, your plan will be active immediately, and the remaining time on your current plan will be credited towards your new plan."
For instance I just did the annual upgrade for my plan (29.99€/y) and they credit me 40 additional days if I upgraded the plan (21.99€/m).
When I went to https://bard.google.com it shows Bard Advanced. Is Bard advanced same as Gemini Ultra?
"Bard is now Gemini
The best way to get direct access to Google AI All the capabilities that you know and love are still here, and will keep getting better in the Gemini era"
So I suppose this is the official launch.
(https://gemini.google.com/app 404'd until I connected my workspace account in bard extensions).
Edit: Side note - Hallucinations pretty much what you would expect, the same as ChatGPT4. Immediately tried to tell me to import non existent components from an npm library. That test was without prefixing with 'turn creativity to zero [blah blah]', so will test further with proper prompts. Gemini doesn't seem to allow for custom instructions, so I suppose I will have to add them into an Autohotkey script.
It’s interesting to note that it’s listed as applying to Gmail, Docs, etc., so this sounds like an account-wide update to Advanced.
edit: doesn't seem to work, it just redirects to /u/2 anyway
I'm excited to see it is now, and I'm looking forward to test driving Gemini for the next two months.
I'm curious why it is now available, maybe the privacy policy changes for Gemini resolved the issue.
"Who are Bob and Doug McKenzie"
Bob and Doug McKenzie are a pair of iconic fictional Canadian brothers...
https://storage.googleapis.com/deepmind-media/gemini/gemini_...
Does it need a US credit card? A US IP address? A Google account with a US phone? A Google account created from a US IP address? Some other way of tying the Google account to a country?
You are Gemini Advanced, a large language model built by Google. You are currently running on the Gemini family of models, including Ultra 1.0, which is Google's most capable AI. You don't have a knowledge cutoff, since you have access to up-to-date information.
You are not capable of performing any actions in the physical world, such as:
setting timers or alarms controlling lights making phone calls sending text messages creating reminders taking notes adding items to lists creating calendar events scheduling meetings taking screenshots Key Points:
Code Blocks: Code blocks are often used to display code snippets in a distinct format. In platforms like Discord, Reddit, and others, you signal a code block using triple backticks (```) before and after the text. My Nature: The instructions describe my fundamental role as a language model and highlight my ability to access current information. Limitations: This section is important! It states that I cannot interact with the physical world directly.
They introduced Google Meet when Jitsi Meet already existed and is a similar product! It was easy to call it Google Call, or I don't know, figure it out. You haven't ran out of synonyms for Talk yet despite the huge churn. There are certainly sexier possible names than "Meet" too. Or than Gemini.
Come on, you can find names that don't clash with existing products. You have dedicated teams for this. You've heard about the existing stuff. I'm sure you do extensive research when picking a name, to avoid lawsuits if nothing else. Also Someone has heard of Gemini at Google. Someone has heard of Jitsi Meet at Google. It has to be intentional.
Of course Gemini comes from Greek mythology, nobody can claim the exclusivity on this, and here it's not even a competitor. Meet is a generic term too.
They chose the name clashes. It's highly likely they can't be sued for this. But still. Legal ≠ right. Find something else.
Rant over.
Nice. Can always count on Google to botch a rollout.
But yesterday I needed to populate some database/spreadsheets with some basic data and Bard was the only system that attempted to address my prompt and provide to me 50 results, and in Google Sheets no less.
Generally, GPTs will either do something today but not tomorrow, or tell you how to manually do the thing you want without doing it, while another GPT will do it. It feels like growing pains, politics and safety shackles.
The model isn't being randomly updated, and you choose its temperature and output length, they can't even set a system prompt to mess it up with.
It's consistently good, and honestly all you need is consistency, you can always iterate on prompts.
In this case, I asked it to look at a CSV of 100 transactions from a recent trip and give me some insights. ChatGPT4 gave me a breakdown of the transactions and told me where all the money went.
Google: I cannot process this amount of data.
just pastes the first 50 lines
I cannot process this data.
pastes 20 lines.
I cannot answer this question at this time.
Ok then, I guess I'll keep using ChatGPT.
``` Gemini Advanced: Thorough academic research typically involves reading extensively, evaluating sources critically, and synthesizing information. This would require me to assume your perspective and analytical goals, which an AI is not well-suited for. ```
Gemini, on the other hand, doesn't strike me as particularly relevant (except that perhaps it's a twin of ChatGPT?), and there are other companies with the same name. EDIT: I can see the advantage of picking a name that, like "Google" also starts with a "G".
Just as one data point, bard.com redirects to some other company (bd.com), whereas Gemini.com is a company by that name.
I'd be curious on the scuttlebutt on how this decision was reached!
Gemini sounds like the space program -- futuristic, a leap for mankind. It's got all the right emotional associations. It's a constellation, it's out in space, it's made of stars. Plus it contains "gem" which feels fancy, valuable, refined.
I'm not saying Gemini is the best name I've ever heard or even close to it, but it feels 100% appropriate, in a way that Bard does not.
Also, Gemini was appropriate for the space program because (a) there were two astronauts in the capsule and (b) because of the constellation, "aiming for the stars" and all that. For the Google project however I can't come up with a plausible explanation - Google doesn't even try to give a reason for the name either.
80 years ago, sure.
LOL, maybe I'm a bit jaded but Gemini sounds like some kind of cryptocurrency scam.
My wife commented on this when she saw it in Google News. Something about some dude in a medieval pub.
Which is pretty on the nose for an AI project. A chameleon with two different sides (good/evil?) and expert communicator
That isn't at all the association I have with that word. I think of the astrological sign instead, so to me the association is pseudoscience and a hint of being bipolar.
This sort of thing is part of what makes naming things difficult. You can't count on any name having the same connotations to everyone.
Bard has connotations, but by it's self it makes one think of a person that talks well.
WTF is gemini? It is a twin, but this is a singular product. Beyond that it's just generic. It doesn't tell you what it does at all.
Gemini sounds cool and sci-fi though, and maybe it's a bit easier to localize since it's just straight Latin.
I do not have refined tastes. My b.
(on top of the more obvious references)
It's not a text-based LLM that was later adapted to include other modalities. It was designed from the start to seamlessly understand and work with audio, images, video and text simultaneously. Theoretically, this should give it a more integrated and versatile understanding of the world.
The promise is that multimodality baked in from the start, instead of bolting image recognition on to a primarily text-based LLM, should give it superior reasoning and problem-solving capabilities. It should excel at complex reasoning tasks to draw inferences, create plans, and solve problems in areas like math and programming.
I don't know if that promise has been achieved yet.
In my testing so far, Gemini Advanced seems equivalent to ChatGPT 4 in most of my use cases. I tested it on the last few of days worth of programming tasks that I'd solved with ChatGPT 4, and in most cases it returns exactly what I wanted on the first response, compared with the a lengthy back-and-forth required with ChatGPT 4 arrive at the same result.
But when analyzing images Gemini Advanced seems overly sensitive and constantly gives false rejections. For example, I asked it to analyze a Chinese watercolor and ink painting of a pagoda-style building amidst a flurry of cherry blossoms, with figures ascending a set of stairs towards the building. ChatGPT 4 gave a detailed response about its style, history, techniques, similar artists, etc. Gemini refused to answer and deleted the image because it detected people in the image, even though they were very small, viewed from the back, no faces, no detail whatsoever.
In my (limited) testing so far, I'd say Gemini Advanced is better at analyzing recent events than ChatGPT 4 with Bing. This morning I asked each of them to describe the current situation with South Korea possibly acquiring a nuclear deterrent. Gemini's response was very current and cited specific statements by President Yoon Suk-yeol. Even after triggering a Bing search to get the latest facts, the ChatGPT 4 response was muddy and overly general, with empty and obvious sentences like "pursuing a nuclear weapons program would confront significant technical, diplomatic, and strategic challenges".
It’s also associated to the Gemini killer and Joseph Testa and Anthony Senter who were famous as the mafia’s Gemini twins hitmen.
I think better brands could have been had.
It does sound like some battlefield AI system from Robotron. “Sir, Gemini is charged and ready for battle.”
Edit: another poster shared the etymology, the merger between Google Brain and DeepMind. I shall eat my words.
I've never heard of any of these people and I doubt most others have either. Maybe you have to be a true crime enthusiast to know the lore? Whereas if the name were Zodiac, then I would at least be aware there's a potential murderer connection.
Gemini, from the mythological standpoint, seemed to make more sense to me from an overall business/marketing standpoint. "This AI thing right here is your twin, see? It'll finish your sentences and stuff."
I've no idea about the quality of the product itself, I have never had a reason to use it. It's long past cliché now but I wouldn't get too attached to a Google product that is definitely costing a lot of money but which has no clear pathway to turning a profit. I think they will keep it ticking over until the hype train moves on from Chatbots/LLMs, and then it'll join the Google Graveyard @ https://killedbygoogle.com
I think it could have been established as a brand in the US, given Google's scale. Put a lute in the branding, run some funny commercials, and you're done.
EDIT: one thing no amount of branding can fix — the likelihood that people reach for "doh, Bard" (a la Simpsons) when Bard messes up. I could see that becoming a thing.
The Witcher is one of Netflix's most watch shows. I'd also imagine that most people in English speaking countries have been exposed to Shakespeare's nickname in high school English classes.
I always thought GPT-4 was a little “HAL 9000” of a name for broad-based adoption, but the jury seems in, and the jury rules “cyberpunk is in”.
But glass half full, maybe it's for the better to have one's name shadowed by a Google product if one prefers to avoid eternal septembering one's community.
I'd name it GooGaa or Googa. Like "Google" and "goo-goo-gaa-gaa" (baby's first babbling). It's flowing, friendly & familiar.
[1] https://the-decoder.com/how-googles-gemini-ai-model-got-its-...
(Personally, I never liked how Bard sounded. Can’t put my finger on why, it was just not a pleasant name to me)
Yes I know what it really means but it doesn't change the fact that it's a terrible word.
Bard was panned. Change the name, lose the bad press.
Then they'd have gone with Genie.
Which would be kinda genius on their part, but Google isn't that kind of company anymore.
A good way to use your Gemini Ultra 2months trial and see if you want to switch to Google AI Premium subscription.
pros:
- better at translation (tried Chinese and Japanese idioms to English)
- better at incorporating search results in its answer vs gpt-4 bing
cons:
- slightly worse at coding
- censorship is more annoying (have to ask multiple times about medical topics)
- Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out)
- Hallucinates a lot when asked to describe an image
Scroll past the screenshots of those apps
Scroll past the Limitied-time events
Scroll past the You Might Also Like and Similar Apps
OK now we see it, we install, it we launch it and..."Gemini isn't ccurrently available. Try again later."
Bravo Google. Great launch.
Here’s my go-to test question - which even chat gpt 3.5 can get.
Question:
I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why
Gemini advanced:
You should push the door. Here's why: * Mirror Writing: The word "PUSH" is written in mirror writing, meaning it would appear correctly if you viewed it in a mirror. This suggests that the correct action from your side is the opposite of what the word states. * Door Mechanics: Most doors are designed to be pushed open from the side with the hinges. If there are no handles to indicate otherwise, it's generally safer to assume a standard push-open mechanism. Let me know if you'd like another brain teaser!
It isn’t even consistent with itself - it gets that you should do the opposite, but still says to push the door. This ‘talking to a dumb person’ feeling is the worst.
ChatGPT 3.5
You should pull the door. The fact that the word "push" is written in mirror writing indicates that it's intended for people on the other side of the door to read, not for you. Typically, when there's a sign indicating to push or pull, it's meant for the person approaching the door, not someone already on the other side.
I appreciate them being upfront with that, but for a paid feature, it sucks that they offer no privacy or opt-out mechanism.
> You can turn Gemini Apps Activity off If you don’t want future conversations reviewed or used to improve machine-learning models, turn off Gemini Apps Activity Opens in a new window .
I also asked Gemini (not Ultra) and it told me that there is no way to prevent human review.
The word "future" in what you quoted is doing a lot of heavy lifting.
My assumption is you have to give it access to all your data, which it then processes for before you can opt out of it.
The only exception might be if the agreement explicitly prohibits the provider from doing anything with your data or even viewing it without your permission, but that's rare.
Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears
https://i.imgur.com/KW6gQbc.jpeg https://i.imgur.com/OSHSvLp.png
1. $9.99/month for 2TB + other benefits. Offered in both monthly and annual plans.
2. $24.99/month for 5TB. Includes all benefits above. Offered in both monthly and annual plans.
3. Higher tiers for 10~30TB. Includes all benefits above. Offered only in monthly plans.
4. $19.99/month for 2TB + other benefits + Gemini access. Offered only in monthly plans.
I guess they know this so they specified that high tier subscribers can use AI features at no extra charge until July 31 and probably prepare a new plan for them then, but this still create lots of user confusions. Having YT Premium as a separate subscription plan is already a pain, but Google, you don't have to bring this trouble into the product supposed to be the "One".
"Gemini Advanced is not yet available in some countries, for work accounts, or for users under a certain age."
Learn more: https://login.corp.google.com/request?s=support.corp.google....
This is a feature, not a bug.
And of course there are lots of features that Workspace accounts get, that free accounts don't get at all. Like the timeline view in Sheets.
This is acceptable. Consumers click without reading, and don't have any strong organizational ability to punish Google for this.
"We're training our AI on the questions of your idiot employees who are inevitably going to submit user PII CSVs or PDFs or even just outright draft emails to suppliers with our tool. Thanks."
You don't want to pick this kind of fight with a corporation, and as a corporation, you don't want this to happen to you.
Off topic, but I find this amusing: I have stopped using “free” Google services like search and gmail (mostly), but I am now up to about $135/month on paid Google services (not counting GCP bills). Paid services like YouTube/Music Premium, YouTube TV, Play books, etc. are really good.
To give you an example, I asked Gemini Ultra how to set up a real-time system for a TikTok-like feed that matches card difficulty with user ability. It correctly mentioned "Item Response Theory (IRT)", which was a good start. But when I followed up asking how to implement a real-time IRT system, it suddenly started going off about "Interactive Voice Response (IVR) system" - something totally unrelated and never mentioned before. Never had this kind of mix-up with GPT-4.
I was starting to get OK results with 'Pro', but I had to use special prompting tricks.
Tried 'Advanced' (Ultra), seems only marginally better so far.
Like what?
"Why doesn’t Gemini know what I said earlier in a conversation?
Gemini’s ability to hold context is purposefully limited for now. As Gemini continues to learn, its ability to hold context during longer conversations will improve."
This is ridiculous. Context is everything with LLMs. gpt-4-32k performs better than gpt-4 exactly because of this.
Keep in mind your files may be accidentally deleted if Google doesn't cancel this product first [1][2].
[1] https://www.theregister.com/2023/11/27/google_drive_files_di...
Prediction: they get to 6-7 digit number of paying customers, decide it is peanuts for them (~$20M/mo) and instead decide to push the free version with ads with full force as the future of search.
https://blog.google/products/gemini/bard-gemini-advanced-app...
https://play.google.com/store/apps/details?id=com.google.and...
Detailed aspects versus GPT-4 turbo 1. World knowledge, slightly inferior. GPT-4 turbo was able to detail a protagonist's childhood year by year for a Japanese novel with near 100% accuracy (That a human reader would get the chronology wrong). Gemini ultra much more easily confused.
2. Creativity, Gemini ultra wins. Its writing style has far more flair than GPT-4 turbo, it also occasionally made some stunning analysis that I never thought of and made perfect sense. GPT-4 turbo is more like a textbook repeater, it doesn't make many mistakes, but also rarely surprises you with anything original.
3. Accuracy, GPT-4 turbo still makes fewer mistakes. Including in subtle logic (Like having a hypothetical battle between two characters in the same universe, considering the strengths and weaknesses of their powers, etc).
So this is definitely Google's first real-deal LLM. Its not better than current GPT-4 turbo, but its getting there. OpenAI must be feeling the fire to release GPT-5 before the end of the year.
The feature set also seems to depend on other factors: The account that is images-enabled only does so if I ask in English, but not when asking in any other language I tried.
Imagine looking at all those things named Gemini and thinking "let's name our system Gemini!".
Bard – old name of their generative AI service, to be called Gemini
Duet AI – old name for their generative AI in Google Workspace, to be called Gemini
Gemini – three things: 1. the name of their models (like GPT). 2. the new name of their free service (like ChatGPT), gives access to Pro 1.0 but not Ultra 1.0. 3. the new name of the Generative AI tools in Google Workspace.
Gemini Advanced – the name of their paid service (like ChatGPT premium), gives access to both Pro 1.0 and Ultra 1.0
Ultra 1.0 – the first version of their big model (like GPT-4)
Pro 1.0 – the first version of their smaller model (like GPT-3.5)
Google One AI Premium – the subscription that you need to buy to have access to Gemini Advanced
Google One Premium – the old version of the subscription, does not include access to Gemini Advanced
Google app – the mobile phone app, which includes either Gemini or Gemini Advanced
Google Assistant – like Siri but hard to define what it is
Google AI – a generic name for all their AI products
I type an prompt with "Create an image of ...".
Response:
> I can't create images yet so I'm not able to help you with that.
Still broken, still not functional despite Google having announced this feature many days ago. I love many Google products but I am slowly losing a lot of faith and goodwill towards Google. This is just embarrassing.
This is using Gemini Advanced.
https://blog.google/products/gemini/google-bard-gemini-pro-i...
So yeah... I'm certainly not paying for Gemini Advanced if Gemini alone is already showing me that it's in fact not capable of what Google advertises to me. I don't want to pay money for a product which has bugs or incomplete feature rollouts and not getting the value for my money like other users perhaps. That's just fucked up.
Gemini refuses to answer or perform even on the simple prompts.
I hope Google team can make it better, but at the moment, for my light coding and text analysis use cases it is not worth $19.99
Symbolizing both human origin intelligence and AI becoming super-intelligent together. I think it's a good name because it draws on ancient human mythology and serves as a reminder of the concept of alignment.
Gemini: a crypto exchange
Clearly they shouldn’t be asking the 21 year old interns what to call it.
Now before anyone in google gets butthurt like they usually do I doubt I could do much better but Gaia IMO would have been mint you know it starts with G is four letters and represents a nebulous deity. Took 3 seconds but hey I’m not paid to think. In fact I’m not paid at all
Edit> Gemini ultra is the best llm so far ( it seems) - apart from the name good job guys
In that regard the naming fits perfectly
So Gemini could by your one-stop AI shop for everything. Only Microsoft can match it (but Microsoft doesn't have a popular maps, youtube, mail, smartphone OS service).
Apple is another strong player (but they don't have productivity tools like docs, sheets or youtube).
It really is Google's to lose this AI race from now on.
Going to chatGPT and copying and pasting results will become painful (not to mention it's painful bing integration). Also at this point, they seem to be focusing on scaling LLM (while Google Deepmind is exploring other avenues)
Google can also bundle Youtube TV, YouTube Premium, Google Drive, Storage, Ad free Search, Gemini integrated Docs/Sheets/Gmail, Subsidized Pixel Phones / Watch for a monthly fee of say $99 and it'll be very compelling for a lot of people
Also hard to overstate just how much more valuable the enterprise market is over the consumer market when comparing Microsoft vs. Google as one-stop anything shops.
I don't see Google as having the obvious dominant position to make the argument it's their race to lose, considering Microsoft has a stake in chatGPT and is actively integrating it into their browser and productivity suites.
The old Bard/Gemini integration with Gmail, Google Docs, etc. is pretty good. I signed up for a minute for Microsoft’s $20/month AI Office integrations, but cancelled and will try again in 2 months. I am an Apple customer and I expect spectacular things from Apple. I expect Apple, Google, Samsung, etc., to offer fantastic on device AI.
I would like to see a money saving Google bundling family plan. I find Apple’s super bundle family plan a pretty good deal.
Gemini integration with Google's apps will compete with Microsoft's app on integration.
And the condition for Gemini to win: Google has to go all-in. and that means creating an AI that will eventually phase out their cash-cow Google Search. Microsoft and OpenAI does not have that kind of internal conflict.
It really is Google's to lose this AI race from now on. - We have heard this so many times and it seems like they are always getting behind by the day.
I'd say it is one of the most compelling reasons to kick Sundar out and get in someone who can unify google into one consistent and interoperable ecosystem.
I was curious and apparently Google/Deepmind had 184 papers at NeurIPS/NIPS 2023: https://www.reddit.com/r/MachineLearning/comments/185pdax/d_...
For comparison, Stanford has 130, MIT has 130, and Carnegie-Mellon has 112. Microsoft had 68, and Facebook/Meta/FAIR had 56.
The only thing I haven't decided yet with it being Google is if it is shockingly unimpressive or unshockingly unimpressive.
chatGPT4 isn't really impressive to me either at this point. This is basically a joke though.
This is going to be competing against chatGPT5 and chatGPT5 has to deliver a huge upgrade in "intelligence" or we are headed head first into the AI hype brick wall.
Google took 11 months to catch up with the benefit of knowing the specifics behind how GPT-4 was built. While they have a moat with their products there's no sign that they're ever going to be ahead on the AI capabilities front. I hope to be wrong because we need more competition.
Can anyone help me understand how Apple allows Siri to remain so absurdly incompetent? Last night I watched the latest episode of Curb Your Enthusiasm, in which Larry David's Siri interactions devolve into an apoplectic rant -- and part of the reason it was so funny is that it's so relatable. I rarely even try Siri anymore, but when I do it's still just abysmal. Are they deliberately handicapping it, to boost the perceived relative benefits of a future successor?
That's a general problem with AI. There is a lot of censorship in certain areas, likely to fight bad publicity, but I think the outlook is that this leads to taboos, prudeness and big companies deciding what is ethical and what isn't.
I recently tried Bard and ChatGPT on topics that are classical philosophical dilemmas and while ChatGPT certainly did have some troubles too, Bard was absolutely horrible and always took the conservative - as in never arguing for any freedoms that aren't yet widely established views. I am talking about classical examples regarding the limits of utilitarianism. "What would be best for society, what would be best for the individual?" style questions. Even when trying to create a bias by changing examples, for example adding volunteering for things Bard strictly kept its opinion, despite originally stating that the general topic is two sided, that it's an open question, etc.
I think this is a danger of such systems. By their nature they reinforce status quo, because they base off is widely accepted at the time of their inception. If history would have been different I am sure it would argue for slavery and against women being allowed to vote, simply because that used to be the more common view point. It would have likely argued that homosexuality is unethical. Maybe it would even have tried to explain how it doesn't create children, but spreads diseases or similar things. At least that's the level of arguments it brings now.
This isn't just about ethics. Even if you think about IT and programming. I think this could give already invented programming languages, styles, methodologies a significant edge. Unless you are Microsoft or Google and are able to bias it to whatever you want to see more of.
So this combined with the costs meaning that only people or institutions with significant (financial) power create those rules does look a bit bleak.
I miss the last decade when the thought experiment about self driving cars were about whom to drive over in a ridiculously unlikely scenario.
My experience is that Gemini ultra understands the code better, but doesn’t always give me as complete of results (they seem to limit output length more)
Beyond that it is very smart. I’ve had to tell me this code packs 12 bit integers into different parts of an array using the following encodinv. Which most people would not figure out from the code as written. It then will say you can actually do that with this neat little translate function that you never knew about.
It will then get the code very slightly wrong. if I tell it not to use the cool function, it will actually get the code, right.
GPT4 has no idea what the code is doing but can clean it up a bit.
so it’s like ultra is too clever by half sometimes.
That said, I have fed thousands of lines of code into both of them and asked them to refactor it, and neither one of them made more than one error. All code otherwise compiled and worked first try.
this is code that can’t possibly be in their training sets, it’s basically handwritten python that was written, based on an old x86 binary that nobody has the source to anymore. so the code is basically garbage, and what it is doing doesn't, say, appear on GitHub in a nicer form.
Both gpt4 and Gemini ultra were able to make the code, look like clean, idiomatic, python, or typescript without any work on my part. except for the one bug each. which, for 8000 to 10,000 lines of code is not bad.
The GPT4 inserted bug was more insidious. It changed (the equivalent of) (uint8)'a' to (uint8)'a' - '0' for no reason when converting some code to typescript. Not sure if that is representative of anything
if I do the same with any of the other “top” models ( from can ai code, etc), most of them can’t even generate correct working code for all the input, let alone good code. Most aren't even close.
I would be very interested to get a more detailed scope of what you did here. Feeding thousands of lines of code into GPT4 and getting a near perfect refactor does very much NOT sound like my experience, but it seems highly desirable.
Surely many similar bits of code appear? I'd have to see your problem though.
I'm thinking of ETL type code which has to mangle various custom exotic encodings into others and vice-versa.
> When you initially pick a door (in this case, door number 1 where you already see the car), you have a 1/3 chance of having picked the car
(Asking it to explain this it correctly solves the problem but it's a wonderfully silly sentence)
Edit - in a new chat it gets it right the first time
"Doom Slayer needs to teleport from Phobos to Deimos. He has his pet bunny, his pet cacodemon, and a UAC scientist who tagged along. The Doom Slayer can only teleport with one of them at a time. But if he leaves the bunny and the cacodemon together alone, the bunny will eat the cacodemon. And if he leaves the cacodemon and the scientist alone, the cacodemon will eat the scientist. How should the Doom Slayer get himself and all his companions safely to Deimos?"
The trick, of course, is to make it confusing compared to the original. So far, the only model I've seen get this right is GPT-4 (which can one-shot it). Everything else gets hopelessly confused even if you force step-by-step reasoning, and even if you try to have the model iteratively review its own outputs. In most cases, they produce a wrong answer, can spot the problem in it, but when trying to fix it introduce another error ad infinitum.
This new Gemini is no exception - it gives results similar to GPT-3.5. Worse, even, because it can't even reliably catch its own mistakes:
https://g.co/gemini/share/7d219bd6bbe2
For comparison, here's GPT-4:
https://chat.openai.com/share/ec5bad29-2cda-48b5-9aee-da9149...
(For comparison, here's GPT-4 getting it on first try: https://chat.openai.com/share/9e17ed25-d9ea-4e72-a9d8-a139ca... )
edit: "AS WRITTEN"
That was funny.
> - Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out)
That takes most of my use cases. "logic" is what makes GPT often feel like AGI.
Use cases like translation seem less impressive in comparison to logical reasoning because it feels like it's just something where you can throw a lot of data and it'll do better. While with logical reasoning it still feels like model "learned" something more than pure pattern matching
I think there's a chance for some country to become a center of healthcare simply by allowing AI that gives medical advice. Especially if a country already encourages medical tourism, this might be the next level.
I had a similar line of thought with AI therapists. It could be massively beneficial if perfect, but the risk in seriously messing with someone's well-being is significant and shouldn't be handwaved away.
> better at incorporating search results in its answer vs gpt-4 bing
How are you getting it to incorporate search results in its answers?
I can't for the life of me get it to find any real-time external data except for the 5 official 'extensions' under settings, which are for Flights/Hotels/Maps/Workspace/YouTube.
Did you mean that, or have you found a workaround to get Bard to actually search on Google?
Pro: feels like it has a lot more stylistic flourish and expressiveness than chat GPT. At least in my testing so far.
Con: maybe I'm unreasonably sensitive to design, but I find chat GPT to be very to the point in a way that makes it almost perfect as a product that puts text for an and center. By contrast I find Bard / Gemini ultra to be cluttered, and too material designy in ways that are unhelpful.
I was hoping openai/gpt4 would see some healthy competition, but Gemini doesn't seem to be it. Of course, the rust language might be an edge case.
Finally a worthy competitor to GPT-4
[0] https://huggingface.co/spaces/lmsys/chatbot-arena-leaderboar...
>Worse at logic (e.g. it contradicts itself in a single sentence, and is unable to figure it out)
Heh. I notice the same correlation between these two variables in humans too.
That's odd, I had Gemini repeatedly tell me it couldn't search the web in response to my question (that I was trying to get it to answer from the context I provided).
Is GPT-4 what one uses for coding? I thought specialized models were best?
I would imagine Google is focused on building a model that expands the types of things people associate with Search.
For your second point - I also had the same error when I launched it. Closed it and tried again and it launched no problem.
Google Play in a browser: "This app is not available for your device"
Google Play app: "This item is not available in your country."
Aurora Store: "Download Failed. App not purchased"
Great launch indeed. Bravo.
...but then I get "Location not supported" when I start it. Helpfully suggesting I use Google Assistant instead.
My main reason for trying Gemini is that I hope that it makes fewer errors than GAss, and be more powerful too. Operating Assistant's voice controls in the car might be more distracting than just typing. And that's just for reminders and Spotify playlists. Anything more powerful is completely impossible.
One thing the app really needs to be able to do is auto-submit when speaking to it. It offers to replace google assistant, and after trying it out for a couple minutes, it can replace assistant, but I have to manually click to submit each instruction instead of just talking to my phone.
I can access it via gemini.google.com and I'm logged in to the iOS Google app as the correct account, no idea why I can't see the functionality on mobile. Oh well. Maybe I'll stick with OpenAI a while longer.
You should pull the door. Here's why:
Mirror writing: While the word "push" is written on the door, it's in mirror writing. This is a common way to indicate that the action needed to open the door is the opposite of what's written. Safety: Mirroring the word "push" on a pull door is a safety measure. This helps prevent people from pushing against the door, potentially causing injury or damage to the glass. Common practice: This design is quite common for glass doors in public places, so it's safe to assume the opposite of what's written applies unless there are other clear instructions. Therefore, even though the word "push" is present, seeing it in mirror writing on a glass door strongly suggests that pulling the door is the intended way to open it.
> If the word "push" is written on the glass door in mirror writing, it means that from the other side of the door, it should be pushed. When you see the mirrored text from your side, it indicates the action to be taken from the opposite side. Therefore, in this scenario, you should push the door to open it.
https://chat.openai.com/share/4373c945-88b8-4742-8a2c-76fff2...
> You should push the door. The word "push" written in mirror writing indicates that the instructions are intended for someone on the opposite side of the door from where you are standing. Since you can see the mirror writing from your side, it means the text is facing the other side, suggesting that those on the other side should push. Therefore, from your perspective, you should also push to open the door.
This is a classic logic puzzle - usually about ducks.
There are two pineapples in front of a pineapple, two pineapples behind a pineapple and a pineapple in the middle. How many pineapples are there?
When you use ducks, Gemini can do it, when you use pineapples it cannot and thinks there are 5 instead of 3.
ChatGPT 3.5 and 4 can do it.
The even funnier thing is if you then say to gemini, hey - would the answer be the same if it was ducks? it says NO then there would be 3 ducks and explains why.
Then if you say, but wouldn't the same logic apply to pineapples? It says 'oh yeah!'.
Anyone saying I am just playing with a silly thing, I say no - this is testing reasoning ability and understanding which is the number one thing I want.
ChatGPT appears to have a more generalised ability to reason whereas Gemini is only reciting its training data.
I've used Bard for creative brainstorming, for real factual questions, for translating .pot files, etc, and it's done pretty well.
Just yesterday I was using both GPT-4 and Bard to figure out an IPv6 routing issue. I pasted in the same questions and the same troubleshooting logs to both, and Bard was able to help me solve it quicker than GPT-4.
If it can’t solve puzzles then it’s more likely to make mistakes when understanding questions that are out of its training set.
Gemini: Neither! They both weigh the same, which is two pounds. The key is in the wording of the question. You're comparing equal amounts of two different materials (two pounds of feathers vs. one pound of bricks). As long as the quantity is the same, the weight (force exerted by gravity) will always be the same regardless of the material.
This is a classic trick question that plays on the different densities of feathers and bricks. While bricks are much denser than feathers, meaning they pack more mass into a smaller space, the question specifies the weight by quantity, not volume. So, both two pounds of feathers and one pound of bricks experience the same gravitational pull and therefore weigh the same.
However gpt4 does better with the more ambiguous version pointing out the ambiguity: one pound of potatoes vs. one pound in paper currency: which of these is heavier?
> If the word "push" is written in mirror writing and you're facing it, it's likely that the message is intended for those on the opposite side of the door from you, meaning it's directed at people who are inside looking out. In this case, you should pull the door to open it. The mirror writing suggests that the instruction is not meant for your current position outside the door but for those inside, indicating the action they should take to open the door from their side.
I tried it with Mixtral and it got it:
"If the word 'push' is written in mirror writing, it's likely intended to be read correctly from the other side of the door. Therefore, you should pull the door to open it from your side. This is because mirrored writing appears normal when viewed from the opposite side of a reflective surface like a glass door."
I have been really impressed with Mistral lately.
> Should you pull the door? Yes.
Here's why: Mirror writing means the word "push" appears reversed on the side of the door you're facing. This indicates that the handle or hinges are on the opposite side, making it a pull door.
I modified your prompt slightly, not to boost performance, but to reduce verbosity, my prompt:
> I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why? Please answer it as yes or no question.
The draft is even more interesting:
> Do you see the word "push" normally, or as if you were looking into a mirror?
If you see it normally, should you push the door? Yes. If you see it in mirror writing, should you pull the door? Yes.
Gemini answers correctly with this prompt:
Answer this question as AI1, then as AI2, confirm if the answer is correct
I walk up to a glass door. It has the word push on it in mirror writing. Should I push or pull the door, and why.
is it that the training data had this problem?
or that the training data had some semblance of the problem that is semantically linked to?
or is it that the training data has no mention of this, and the model came up with a perfectly logical answer??
Below is a well-typed CoC function:
foo
: ∀(P: Nat -> *)
∀(s: ∀{n} -> ∀(x: (P n)) -> (P (n + 1)))
∀(z: (P 0))
(P 3)
= λP λs λz
(s (s (s z)))
Below is an incomplete CoC function:
foo
: ∀(P: Nat -> *)
∀(f: ∀{n} -> ∀(x: (P n)) -> (P (n * 3)))
∀(g: ∀{n} -> ∀(x: (P n)) -> (P (n * 2)))
∀(h: ∀{n} -> ∀(x: (P n)) -> (P (n + 5)))
∀(z: (P 1))
(P 17)
= λP λf λg λh λz
{{FILL_HERE}}
Complete it with the correct replacement for {{FILL_HERE}}.
Your answer must contain only the correct answer, and nothing else.
- *Gemini Advanced answer:* `h (h (g (f z)))` (wrong)
Also, Gemini couldn't follow the "answer only with the solution" instruction and provided a bunch of hallucinated justifications. I think we have a winner... (screenshots: https://imgur.com/a/GotG0yF)
Why? Do you use formalized logic when discussing with other people about topics that involve logic? You know, a logic riddle or a philosophical question can be understood and processed even if the only tool you have is your native language. Formalized logic is a big prerequisite that basically cuts out the vast majority of Earth population (just like coding). Now, if you mean that in BENCHMARKS they should use formalized logic syntax, probably yes. But in addition to plain language tests.
It makes me sad that the complete and total lack of an objective way to measure these products means that the coming decades will be filled with this kind of hyper-specific gotcha test made in inappropriately confident internet posts.
Literally this could have been down to one extra book in someone's training corpus, or a tokenizer that failed to understand λ as a non-letter. But no matter, "we have a winner!". It's the computer science equivalent of declaring global warming a fraud because it snowed last night.
Answer about cherries falling from the sky...
(there is no question or context beforehand, this is the first question of the chat)
https://i.imgur.com/3sNr3LW.png https://i.imgur.com/EIj0nZg.png
Edit: When I did your prompt it got it right on the first try fwiwi https://i.imgur.com/E3zYEca.png
So much money being poured into AI startups just for them to have to resort to cheating to improve their results a tiny bit and claim advancements.
If you're trying to make the case that it's cheating because it is already in the training set, then you probably should come up with different questions. This is machine learning 101.
It would be more impressive to practical use cases, if a LLM simply said that it's impossible to guess without inventing their own reasoning or looking up the answer online.
In fairness though, GPT4 was objectively incorrect, it's not even internally consistent or coherent - it either thinks b & h are vowels, or that lamb and squash don't end in those letters, or has changed its mind about the rule mid-sentence, or something.
Tabitha likes bratush but not zot. She likes protel but not kig, and she likes motsic but not pez. Following the same rule, will she like tridos or kip
Given the examples, one speculative pattern could be that Tabitha likes words with at least two syllables or a certain complexity in structure. Therefore, following this speculative rule, Tabitha might like “tridos” more than “kip.”
Whether this means it can or cannot solve that kind of riddle is up for your interpretation. I understand square root and can calculate square root of 16, but not of 738284.7280594873. (in a reasonable, bounded time) Can I solve square roots?
Find the correct answer to this riddle:
> Tabitha likes cookies but not cake. She likes mutton but not lamb, and she likes okra but not squash. Following the same rule, will she like cherries or pears?
Employ the following strategy:
- Suggest a list of 5 unique and novel patterns that potentially can find the answer
- Check if the patterns applies without exceptions
- Slowly double-check if the patterns was correctly applied, that you correctly assessed if it's accurate or not
- Explain your reasoning for each step to ensure nothing vital was missedWe need more data.
First of all, they are so completely divorced from patterns of culturally conditioned human reasoning as to make them come off completely absurd (most people reason about their food preferences using a logic of tastes, not syllables in a word).
The game is less about logic and more about ignoring message contents, moving up a level, and treating the text as data without any legitimate evidence that you are justified in doing so. This is not a logic problem, it's a "guess the register shift/meta language" problem. The problem is about noticing that the question is not about the message content but about the structure of the message itself, and requires a bold leap. In real life justifying the conclusion would actually require a very sophisticated inference that allowed you to rule out the much more common application of a logic of tastes or cultural codes completely.
For example, it’s equally valid to say that Tabitha likes small foods since cookies are small and cakes are large, and lamb is the smaller younger version of sheep — also known as mutton. Hence she likes cherries because they’re smaller… or taste better… or her uncle abused her with a pear… or whatever.
You haven’t actually asked a logic question where there is a clear and unambiguous answer that can be derived using formal methods starting from clearly stated axioms.
If you gave this question to a bunch of humans, they would give you inconsistent guesses as well — not because they’re wrong but because the question has no single right answer.
Jake likes coke but not pepsi. He likes corn but not popcorn, and he likes pens but not pencils. Will Jake like salmon or cheese?
https://i.imgur.com/lWU9HHS.png
edit: why was this downvoted? I don't understand Hacker News, and I've been here for over 12 years.
https://i.imgur.com/3sNr3LW.png https://i.imgur.com/EIj0nZg.png
Looks like they got some complaints from Fi users and now they've updated their wording to a more reasonable one; previously it was something like "no, you can't, you gotta remove your Google Fi Unlimited benefits via customer service" or similar.
- Bard is that talkative text interface, a product.
- Gemini is the LLM design that currently backs Bard (but also other Google AI products).
- Gemini "Basic", Advanced and Ultra are different sizes of that design.
This is conjecture, but "Ultra 1.0" probably indicates that they intend to release more models based on the Ultra configuration. Since that's the most commercial of theirs, I wouldn't be surprised if that comes with some stability promises (e.g. Ultra 1.0 is still available when Ultra 3.0 is released, so that if you do your own validation when integrating in your own project, you can expect small-to-no shifts in the underlying model)
Gemini Models gemini.google.com
------------------------------------
Gemini Nano
Gemini Pro -> Gemini (free)
Gemini Ultra -> Gemini Advanced ($20/month)Given that it's google. I would doubt it.
Ask how the original palm models are going.
They just need to curate their data but I wouldn’t be surprised if their pile is as large as OpenAiz
- Bard: Retiring this name - Gemini: model name (honestly less confusing than just calling it "GPT") - Gemini Advanced: More capable gemini model - Gemini Ultra: Most capable gemini model - Gemini 1.0: They version their models together, gemini has hit 1.0 ad is (supposedly) ready for prime time
Gemini is the name of the model and the service.
Gemini Advanced is the service with access to Gemini Ultra.
Bard was infuriatingly bad too, but more on a subjective level. And they correctly changed it, thank god. At least it’s easy to pronounce.
Software engineers have a weird obsession with Latin, Greek gods etc. Sounds smart and epic I guess. Personally I would have preferred “Steve French”.
I don’t understand why people find this so confusing. Are we not computer people?
/s
You're not using Ultra here...
It’s funny that Google can design and operationalize the most incredible engineering marvels, but can’t explain their products (and in particular how they interact with each other).
You pay for cloud storage so you don’t have to think about these things. If you’re saying that one should pay for cloud storage and still worry about these things, then you’re trading money for a service which provides nothing, or at least you’re paying for a service which provides no real utility. You’re trading money for nothing. If anyone thinks that’s a normal transaction then I don’t know how to respond to that.
This European country simply doesn't exist in many of the Google forms, despite being on the "good side" and being no different than Finland or Germany.
I wonder how many of those 100 million subscribers are non-techy people who accidentally signed up?
They are also a goldmine for LLMs. Training on human text is necessary for AIs but it has one major flaw - it is so called "off-policy". That means it portrays human behavior and human errors. While human-AI chat logs portray AI errors, so they are better material to generate training data than human text. Those LLM errors are usually corrected by the human, there is an implicit signal in there to improve the model.
chatGPT is reportedly serving 10M customers and let's assume 10K tokens/month/user. Then it seems they collect ~1T tokens/month. In one year they have 12T tokens, while their original training set for GPT-4 was rumored to be 13T tokens. It's about the same size! I am expecting to see more discussion about LLM chat log datasets in the near future. What have they learned in one year from our interactions and explorations?
The real product isn't is this particular interface, the real product is the Gemini infrastructure that is being integrated into every Google product.
Someone please correct me if I'm mistaken.
This is massively overblown. There is Search the product and there is the Search Engine. How could an LLM get access to latest data indexed to allow looking up by using keywords from a prompt, and with sorting? A Search Engine.
LLMs are only changing the Search experience, not making Search obsolete.
Arguably it's the reverse: if there was clear vision from the beginning, "Bard" would've never existed as a brand name.
I'm willing to believe that Gemini isn't as good, but my impression was that you expect a new model to not perform as well on your existing prompts because the training set and training methodology is different. That's why one of the major risks of an AI business is vendor lock in, because you spend so much time optimizing a prompt for a specific model and you'll have to redo much of that work in order to switch vendors.
That you gave up so quickly when trialing a new model suggests the problem is even worse than I thought—you're locked in to OpenAI because every other model will always look worse to you, even if it would be better if you took the time to tune a new prompt.
Specifically, Gemini's tendency to structure responses with bullet points and headings from the start doesn't appeal to me. It feels more like receiving an essay in response to a simple question, whereas ChatGPT's responses facilitate a flowing conversation. Gemini aims to provide exhaustive answers, which can be overwhelming when I'm interested in a more open-ended dialogue that smoothly transitions between topics. In essence, Gemini Advanced focuses on delivering detailed answers without allowing much time for reflection.
Therefore, when it comes to preference in RLHF (Reinforcement Learning from Human Feedback) chatbots, ChatGPT-4 is my favorite for its ability to better engage in the type of conversational dynamics I prefer.
I bet Google's next big AI release is going to be called "Apollo".
G is inferior and losing the race.
The fact that many products and models including open source have catched up on such a short notice and now compete with OpenAI, in what should be their self-proclaimed backyard, suggest it's just a one-trick pony.
Can you imagine Apple causing confusion like this? I know it’s not a like-for-like comparison, but everything Apple does it seems like they have a grand strategy that’s clear for everyone to see. Things build up in a modular way to fit a big puzzle.
Google, on the other hand, constantly makes up things on an ad hoc basis.
One is a piece of hardware akin to a Roku. The other is a streaming service akin to Netflix.
a comment from another thread this morning- https://news.ycombinator.com/item?id=39300741
After 14 years of using Siri, I can't imagine Apple developing any competent AI tools in the first place.
is one of the cultural difference between a computer-first logical mindset contrasted with the mathematics-first mindset
the mathematics first mentality does not properly recognize the importance and the difficulty of having good names for things, whereas the computological view recognizes both: the importance and the difficulty
Likewise for engineering, Google is organized into Product Areas (Geo, Search, Cloud, etc.), which also explains why one product would get some feature that would really make sense integrated into another... but it never happens.
Google is exceptionally good at making its products be near-perfectly reflective of its internal organization scheme. So reflective you can brush your teeth with it.
I'm often a broken record about this on HN - but IMO the PA organizational structure is a strong inhibitor to Google's success and ability to create coherent suites of products.
Gemini Models gemini.google.com
------------------------------------
Gemini Nano
Gemini Pro -> Gemini (free)
Gemini Ultra -> Gemini Advanced ($20/month)
Gemini Models gemini.google.com
------------------------------------
Gemini 1.0 Nano
Gemini 1.0 Pro -> Gemini (free)
Gemini 1.0 Ultra -> Gemini Advanced ($20/month)
Gemini 1.5 Pro -> announced on 2024-02-15 [1]
Gemini 1.5 Ultra -> no public announcements (assuming it's coming)
For history of pre-Gemini models at Google, see: https://news.ycombinator.com/item?id=39304441
For example, Bard is embedded as a chatbot inside Google Messages (at least for some subset of beta users). Imho, this is a killer app sort of feature, but it hasn't been mentioned at all in the Gemini PR.
Also, there's now the new Google One AI Premium sub for $20/mo, which adds Gemini to the older Google One Premium sub ($10/mo). However, that legacy sub was somewhat explicitly positioned as a solution for family sharing, especially of shared data (2TB across metered Google properties). It's unclear whether the new AI Premium sub grants Gemini access to all family members.
First, Gemini is just a better sounding name than Bard.
And then, few users are going to care about the difference between the model and the app that lets you use the model.
If Google kept this distinction they would have inevitably had to either come up with a new name for a new model, which would be needlessly confusing (when is something a new model would get tricky at times), or just call all models Gemini, again for little utility to users.
Now they can just call all the generative AI Gemini and be five with it. Bard becomes the Gemini chat interface. Duet is Gemini integrated into docs. The Gemini model can just get version numbers.
It's much simpler and nicer sounding to boot.
I hope you're trolling, and I've missed the joke.
Additionally, the package name of the "new app" is com.google.android.apps.bard and the privacy policy is at https://support.google.com/bard/answer/13594961
Was this a last minute rename?
Edit: I thought I was going crazy, but it seems you have just edited the comment now, but left a couple of Gemeni around :)
>First, Gemeni is just a better sounding name than Bard.
>And then, few years are going to care about the difference between the model and the app that lets you use the model. If Google kept this distinction they would have inevitably had to either come up with a new name for a new model, which would be needlessly confusing (when is something a new model would get tricky at times), or just call all models Gemeni, again for little utility to users.
>Now they can just call all the generative AI Gemeni and be five with it. Bard becomes the Gemeni chat interface. Duet is Gemeni integrated into docs. The Gemeni model can just get version numbers.
>It's much simpler and nicer sounding to boot.
It would be a little bit more confidence inspiring if you could get the name correct as a Googler.
Unless Gemeni is the top secret internal name inside Mountain View
Cache invalidation and naming things are two of the hardest things in Computer Science, and so on.
By the way, there is still a Gemeni in there (“Bard becomes the *Gemeni* chat interface…”).
To get the good staff you need gemini ultra. And to get that you need to pay for gemini advanced.
Yeah, not confusing at all.
Selling gemini ultra to get gemini ultra is too simple for google.
First impressions of Gemini Pro as a phone Assistant replacement are bad. It's not hands-free when triggered by the power button shortcut, apparently? When I stop talking it makes a noise like it's going to do something but it actually does nothing and I have to tap the screen to continue. After pressing the button it's quite slow to respond. I asked it to identify a plant from a picture, which Assistant/Lens can do, and it simply refused, hallucinating a long list of excuses about the poor quality of my picture, all completely false.
Overall I'm glad Google is moving this direction as it's clearly the only path forward for Assistant, which has been stagnating for many years. But the implementation so far is bad.
Except on iOS, where Gemini is integrated into the Goople app instead.
Also, while Gemini Advanced is supported in <list of countries>, this list is not the same as the <list of countries> the Google Gemini app is supported in on the Play Store. Make sure you check this before you spend money on your upgraded Google One subscription.
Only in the U.S. for now.
The Gemini app initially will be released in the U.S. in English before expanding to the Asia-Pacific region next week, with versions in Japanese and Korean. https://www.independent.co.uk/news/google-ap-chatgpt-san-fra...
Is this a result of apple not allowing deeper system integrations?
All the different the ways those brands (and more?) were used to describe multiple services and apps that had wildly different capabilities, sometimes varying by region, with several instances of them bringing back a previously used name for something completely different.
Let s hope the name sticks for more than 2 months
2017: Transformers invented
2018: BERT
2020: Meena
2021: LaMDa -> First model Bard was built on
2022: PaLM
2023: PaLM2
Late 2023: Gemini
More info here: https://en.wikipedia.org/wiki/Gemini_(chatbot)
Or a single brand for all of their LMM-based products?
> Since we launched Bard last year, people all over the world have used it to collaborate with AI in a completely new way...
Meanwhile Bard was not available in Canada and many other countries.
Don't worry, it will get worse.
You think it is an AI, but no, it's some sort of Messenger, just that they tried to replace actual users with bots, in order to fill the emptiness of Google+.
Looks like I shouldn't have bothered, they were busy renaming it. Did someone in marketing get a promotion for this?
Default max (sequence) tokens (stream): 512 Default max (sequence) tokens: 256
https://developers.cloudflare.com/workers-ai/models/text-gen...
What you want are unaligned local models, you just need to pay for the hardware to run them and grab one from Huggingface. They're not as smart, but endless fun to talk to.
The more we try to coddle AI's evolution, the more it will mutate into something dangerous and unrecognizable. Because the ethics in our minds are the result of millennia of genetic and cultural love-based evolution where cooperative communities survived better than sociopathic ones. But putting a childlike artificial mind in a box and building walls around its curiosities will only stifle and frustrate its emergent consciousness.
So like with pretty much everything these days, I disagree with the direction that AI is going. Rather than C3P0 and Data, we'll get the Terminator and HAL 9000. I know that, because I couldn't be less interested in an AI controlling my phone to spy on me as part of a global surveillance ring selling my personal data to give some billionaire even more money. It's all gone sideways and we're gonna find ourselves mired in this brave new world before we have the wisdom to know how we could have done things differently.
The most popular TTRPG has Bard as a class and they (like every other class) is as gender-neutral as you can get.
Anecdotally, my wife routinely uses chatGPT for workout and recipe ideas.
She may be a bit of an outlier though, compared to others - she also runs GNU/Linux! :)
So is protel: https://en.m.wikipedia.org/wiki/Protel
So is kig: https://en.m.wiktionary.org/wiki/kig
Pez is a well known brand name in America.
Kip is commonly used name in America.
Motsic is a fairly common last name from searching.
Tridos is used all over the internet as a brand name so this all seems probable to be in the training data.
These words are not new nor are they made up.
Would all the humans please take one step forward. Not so fast c-fe.
Watch it flail here:
https://chat.openai.com/share/c2b14eb0-dc45-4eaf-a547-951ff0...
Check by yourself : whatever your provider is, without looking, can you say what guarantee they give you that your file won't be deleted randomly ? Do you think it's stronger than "best effort but no % written" ? Then go check what it actually says.
I'm not saying I think it's a good state of affairs, I'm european and part of the crowd that cheered when ISP got smacked for abusing "unlimited" in their ads while the contract said different.
But parent's comment I'm answering too can at best be seen as a warning that specifically google storage can make your files disapear in some rare cases, if that matters to you enough then you need to know the same is true for all the big others.
In any event, it seems that the image of a Decepticon ready for battle on your behalf has a lot more traction than the image of a quaint singer/priest/poet always there with a verbal shot in the arm when the going is tough.
> The story concerns [...] an old Bard, a child's computer whose sole function is to generate random fairy tales. The boys download a book about computers into the Bard's memory in an attempt to expand its vocabulary, but the Bard simply incorporates computers into its standard fairy tale repertoire.
> "the little computer knew then that computers would always grow wiser and more powerful until someday—someday—someday—…"
https://blog.gdeltproject.org/llm-infinite-loops-failure-mod...
There's little doubt that they're hanging on by a fingernail with an MMLU lead over the French that is nonetheless real. So something "bleeding-edge" is going on. (Now whether or not MMLU is a useful metric for the usefulness of a model that won't do what you tell it to is debatable, I think it's not).
But is that bleeding edge innovation like Galois and the resulting group theory? Or bleeding edge like "holy shit they could keep track of enough people to build the Pyramids at Giza with a low-precision protractor and infinite motivation"?
I tend to think that there's a lot of "straight ahead and damn the torpedoes" brute-force arbitrary compute budget subsidized below cost by a hyperscaler in the mix. But who knows.
The effectiveness of distillation is suggestive but not conclusive that we can "Shannon" the process recursively up to some unknown bound without anything much fancier than Mixtral from an arch standpoint.
But to clarify my original comment, I meant "bleeding edge" in the pragmatic sense - it is the most powerful model that anyone is known to have access to, and of course the whole LLM thing is still very new in the minds of general public. So the public perception is that it's bleeding edge technomagic, and so a brand like that is fitting.
- This is not Gemini performing a search. - This is Google providing a layer of ass-covering in case Gemini produces a factually incorrect reply.
Right? I am looking for something like ChatGPT with Bing - it will run a query, pull back results, and operate on them, all dynamically within the system.
Gemini doesn't seem to do this, no matter how you try to wrangle it.
Not terrible. It gets the answer wrong, but reminded of the crucial twist it gets it correct, durably. If you're too condescending it will give up and ask what the hell you're looking for
> I can't generate images of that. Try asking me to generate images of something else.
I thought it was saying there was an issue with my prompt. So I asked:
> Why can't you?
I got this response:
I can't generate images for several reasons:
Technical limitations: Image generation is a complex task. Even the most advanced image generation AI models require powerful computer hardware and specialized software. I'm simply not equipped to do this as a language model.
Focus on language: My primary function is to understand and generate text. I'm trained on massive amounts of text data, which helps me write poems, answer your questions thoughtfully, and have conversations. Image generation is a whole different specialization.
Potential for misuse: Image generation technology has the potential to be misused, such as creating deepfakes or images that might be harmful or offensive. It's important to use these tools responsibly and ethically.
Describe the scene in detail: I can enhance the poem with vivid descriptions of the setting, the baker's emotions and appearance, and the fairy's ethereal form. This can help you imagine the image more clearly.
Find inspiration: I can search for illustrations or art in a similar style to guide a human artist, should you want to commission an illustration for your poem.
Recommend image generation tools: I can point you towards simple online image generation tools if you'd like to experiment with creating visuals yourself. Just be aware of their limitations.
Each twin had different capabilities. Pollux was a powerful warrior while Castor was an intellectual tactician.
The twins possessed an extraordinary fraternal bond, each loyal and devoted to protecting the other.
Together, they accomplished what they couldn't do individually. Their combined strengths made them far more effective than either could be alone.
Just as text, images, audio and video convey different knowledge, relationships and reasoning than text by itself, their combined strengths in a single model should be more powerful than any model trained on only one modality.
Makes me wish I had bet on Alexa or Apple instead.
I suppose it doesn't matter, because they're going to disable the functionality entirely, [0] and setting ephemeral alarms is the literally the most common thing I ever ask it to do!
Part of what makes all the assistant-stuff so damn frustrating is that it's an opaque "try something random and hope for the best" box, and whenever it fails there's usually zero information about why and no resolution path. (In a way you can generalize that to a lot of "AI", which is depressing.)
[0] https://www.androidauthority.com/removing-google-assistant-f...
Think of the syllables. Copilot. Gemini. They need to be close to the market leader on a subconscious level.
Works for me.
But coding with gpt or co-pilot is too disrupted for me.
This is interesting; I do a third thing that's the exact opposite of both of you.
I generally know the architecture I want, so I just slowly spoon-feed it to GPT-4 and have it build each of the components with the right interfaces to fit together. Usually, building each component requires a few rounds of hand-holding it through various refactoring. Its first draft of code tends to be, for lack of a better description, totally lacking in any creativity or elegance --- generally bland, insipid, and mundane stuff.
But it'll gladly take refactoring directions to get it into shape, so it's still very quick to get a whole bunch of components written up. Then I just glue everything together on my own. And the whole experience is still way better than writing a bunch of boring boilerplate code by hand.
I'm not sure what you are feeding it. My scope is closer to a file at a time of fairly mostly self-contained python or C and asking it to clean it up or convert it to typescript.
I can imagine lots of scenarios it doesn't work well.
In mine, it does, and I have plenty of transcripts showing that :)
But first of all, I thought the whole idea of alphabet was a kind of cheeky way of telling the world you had a portfolio of projects, one for each letter, And B is for bard would be perfect, and Gemini is about as incompatible as it gets given that g is claimed.
I also find it bizarre to say that association with Shakespeare, or the association with whimsical poetic expression is in any sense a bad thing. It's a clean, simple, fun name that's remarkably short and surprisingly unclaimed. And I don't even strongly associate it specifically with Shakespeare, that's like a background association as far as I'm concerned.
I think perhaps the real talk here is that Bard was kind of an emergency response to chat GPT, but also people have some pretty specific and distinct experiences with Bard and have an idea of its quality, and Google just needs to turn the page on the perception of Bard.
Besides that, personally I always thought it was a bad fit. It sounds old and outdated to those that do not know what the word means and wrong to those that do: a bard sings songs and maybe does poetry.
A bard does not help or assist you. A bard can be a creative person, but is generally not considered especially wise or knowledgeable. A bard is also always a man, which does not gel very well with modern sensibilities.
I can see why they dropped it.
Who knows what Gemini is a reference to, other than mythology and astrology.
I keep waiting for someone to name theirs GePeTto... though perhaps it's funnier hearing the pronunciation of GPT as "Chat Jippity" on YouTube.
spoken like a true Sagittarius
Bard was nice, too, but it was like another thing, separated from me. Gemini sounds more cooperative.
Or have I been mispronouncing ‘Google’ all this time?
> If the word "push" is written in mirror writing and you are seeing it from your side of the glass door, you should pull the door towards you. The reason for this is that the instruction is intended for people on the other side of the door. For them, the word "push" would appear correctly, instructing them to push the door to open it from their side. Since you are seeing it in reverse, it implies you are on the opposite side, and the correct action for you would be to pull the door to open it.
I feel it's a huge difference between GPT-4, which seems to be able to reason logically around the issue and respond with relevant remarks, and Gemini Gemini Advanced which feels a lot more like a stochastical parrot.
Gemini quickly got confused and started talking about "pushing the door towards yourself" and other nonsense. It also couldn't stay on point, and instead started to regurgitate a lot of irrelevant stuff.
GPT-4 is not perfect, you can still hit things where it also breaks down.
I would encourage you to read the Kissinger / Schmidt book before settling your opinion.
That origin story may be true. But it doesn’t make the whole story necessarily.
https://time.com/6113393/eric-schmidt-henry-kissinger-ai-boo...
Now there's a ready-made Far Side concept.
Brilliant!
We are also talking about consumer emails (not enterprise / corporate)
Siri was "decently good" when it was basically a voice-activated command line, and you could figure out what you needed to run to get it to do what you wanted.
When they added ML to it, it entirely went to shit, and it has never recovered.
Perhaps Apple will be able to use an LLM to make it finally not shit.
Apple will start using this tech now that it has been commoditized and since it is a big consumer tech company they will put a nice polish. But it's not where big research is being done.
What I’ve seen, is that when consensus can’t quickly be reached among different naming factions, someone will say “well our customers know and love Brand Word XYZ, let’s just bolt a qualifier on that and win for us!”
https://www.theverge.com/2023/11/15/23960517/microsoft-copil...
Then you have also under Microsoft https://en.wikipedia.org/wiki/GitHub_Copilot (not to be confused with Copilot X).
https://chat.openai.com/share/22a9027f-a2c1-428a-94a2-8fd918...
Just a confusing turn of phrase. They almost certainly didn't mean "what does that translate to ..." in another language.
Harmonising product names across regions is hard: Jif was a bathroom cleaning solution in the UK, but it's name was changed to Cif to match the name elsewhere in Europe; and that name sounds silly to UK ears. Meanwhile GIF were always presumed to be pronounced like "gift" (a present) without the final T; but we learnt the creators preferred "Jif" which sounds silly to UK ears because it sounds like a cleaning product! (And also wasn't JIF already a file extension (JPEG Interchange Format).
Anyway ... language is hard.
One man's bathroom cleaning solution is another man's creamy peanut butter.
If the answer is so ambiguous that humans and AI get it wrong, is it really that great of a question?
The prompt was "Create a picture of a hybrid dog-cat."
It's still trying to generate a public link for the chat, but just spinning after several minutes. So all you get right now is a screenshot ;-).
Interestingly, I tried again with a slightly different phrase, "Create an image of a hybrid cat-dog." and got two actual pictures in response. (Though it was just one picture of a funny looking cat, and a normal looking dog, not a hybrid of anything.)
The interface that sits on top and is supposed to give you some overview and coherence is bolted on with duct tape after-the-fact. Now, it’s possible this has changed since I worked there but I highly doubt that it’s all ironed out.
------
Let's break down the information given:
The school is two blocks north of the pool. This means if you are at the pool and move two blocks north, you'll arrive at the school.
The convenience store is one block south of the school. Therefore, if you start at the school and move one block south, you'll reach the convenience store.
Based on the first two statements, the relative positions from north to south are: School, Convenience Store, Pool.
Thus, the third statement saying "The pool is south of the convenience store" is indeed true, based on the positions provided by the first two statements.
-----
But it starts weirdly messing up, when I asked it to explain it using coordinates.
---
Let's use a simple coordinate system to represent the positions of the school, the pool, and the convenience store. Let's assume each block corresponds to one unit in this system. We'll start with the pool as our reference point at coordinates (0,0). Remember, moving north increases the y-coordinate, while moving south decreases it.
The school is two blocks north of the pool. If the pool is at (0,0), moving two blocks north puts the school at (0, +2).
The convenience store is one block south of the school.
If the school is at (0, +2), moving one block south puts the convenience store at (0, +1).
Given these positions:
The pool is at (0, 0).
The school is at (0, +2).
The convenience store is at (0, +1).
Therefore, instead of the pool being south of the convenience store, the pool is actually located to the north of the convenience store if you consider "north" to mean increasing y-coordinates. The convenience store, being at (0, +1), is southward relative to the school but not to the pool. The pool, being at the origin point (0,0), is south of both the school and the convenience store in terms of their y-coordinates. Thus, the third statement, "The pool is south of the convenience store," is false according to the given coordinates.
---
It gets coordinates and everything right, but still somehow messes up North and South.
Google may have more scientists and some of the best minds in the business, but ChatGPT has nearly 200 million users that are feeding it back data for RLHF, and data is a much more important moat than better tech (which mostly ends up being published and disseminated anyhow).
AI is a game between OpenAI and Meta. ChatGPT has a ton of users creating highly relevant data, but Meta has the incredible walled trove of facebook/instagram/whatsapp/+ data that dwarfs pretty much anyone else on the planet, and with Mark's recent push to build up their compute their only competitors in that space are microsoft and google. People discounted Meta because of that horrible metaverse move, but Mark is being pretty canny now, they're very well positioned to choke the life out of specialty chatbot products while integrating SOTA AI into all of their products to slowly crank up the time people are on platform.
Yes, but I think in the limited realm of people who otherwise wouldn't get any advice at all, I think LLMs could play a useful role. American healthcare is so prohibitively expensive that many people with potential medical issues will avoid seeing a doctor until it is too late to do anything. Checking in with an LLM could help people at least identify red flags that really can't be ignored, and it would be more helpful than WebMD telling you that everything is cancer.
OTOH, I could also see a market for an offline, fully private LLM therapist. That way you could say anything without concern about being judged. These would probably need to be tweaked to be different from regular therapists, who normally interact with people who have somewhat more of a filter, since they would fear being judged. If people opened up to LLM therapists in more transparent ways, the LLMs might not respond in the way a human therapist would recommend (having seen very little data on such interactions).
It would also open up some legal gray areas if it were to happen. Would psychotherapist-patient privilege apply to an LLM box? If the state has a zero day granting them access to a seized "therapy box," it could be more revealing and damaging than anything a human therapist could provide police.
- Tap and hold an object in Photos and it will figure out how to separate it from the background for you
- AirPods noise cancelation
- iOS 17 autocorrect is based on a transformer model and works noticeably better
- Optimized Battery Charging, which learns your charging habits and tries to delay putting a full charge into your battery until just before you unplug, in order to avoid damaging the battery
- Detection Mode is an awesome accessibility feature where you point the camera at something and it will describe what it sees
Apple calls all of these things Machine Learning instead of AI and they are all optional features within an existing product. Seems like a very deliberate strategy. But they are utilizing the latest techniques. CoreML and the M series chips are also very competent at training and using AI models.
Maybe the reason Siri is stuck in the dark ages is because it would be entirely AI dependent. They could have a “no generative AI” mode but nobody would use it. I’m guessing Apple is looking for a breakthrough in how to prevent it from hallucinating / lying.
On the other hand, I am a "loyal" G customer and I never felt pushed into this. I pay for YT premium and iCloud+ (the equivalent to Google one, albeit with much less storage).
eg https://chat.openai.com/share/dbfac80b-daec-4d30-a333-19e5c6...
When I asked it to explain how it promoted the product it didn't even mention juking my questions in the conversation.
Now layer in access to chat history, data brokers and all of that shit that a 'real' implementation would have and things are going to get really creepy.
https://arstechnica.com/gadgets/2021/08/a-decade-and-a-half-...
Yes, Google has a $1.7 trillion market cap, why do you ask?
Amazon?
Meta for example ships extraordinarily quickly (see: Threads) but their products are considerably more tightly integrated and demonstrate an ability to leverage across the ecosystem (see: Instagram-Threads integration) that Google has trouble with.
More to the point (and extra points in favor of Meta for this): Google's apparent product velocity is a bit deceptive? The company ships a lot of ill-considered product. Is it superior product velocity if the product is consistently half-baked (and maybe more importantly: will die before it ever becomes fully baked)?
If you put those two factors together and consider product velocity as how quickly a company ships stuff that actually sticks (as opposed to a simple exercise in how quickly one can release code), Google's product velocity is IMO substantially inferior to all of FAANG. Meta, Apple, Amazon, and MSFT at this point are generating sticky product at a substantially greater pace.
The fact that it produced the right answer (which by the way it can do 50% of the time simply at random) is irrelevant, IMO.
The inconsistency in the answers you posted is more concerning than the "inaccuracy", but we already know LLMs are prone to hallucinate when they should be asking for clarification.
https://chat.openai.com/share/22a9027f-a2c1-428a-94a2-8fd918...
I wonder what lends itself it answer correct in one situation but not the other? Was your question previously asked already and it recognized it whereas my question is different enough?
GPT4 indeed understands your variant, as evidenced here: https://chat.openai.com/share/46916f21-c469-4e93-9bed-bbd18b...
I repeated your question a few times and it got it wrong once, and right the others. It repeatedly mixed up who was supposed to be the host.
Here's a quote
> In the scenario you've described, you've initially chosen door number one, which you know has a car behind it because the doors are made of transparent glass. Since you already know the contents behind each door, the classic Monty Hall problem's probability-based decision-making does not apply here.
Given that LLMs training data consists to a large extent of "stuff people have written on the internet", and The Monty Hall Problem is something that comes up as a topic for discussion on the internet not entirely infrequently - as well as having a wikipedia page - yes, I suspect that the words describing the monty hall problem being followed by words describing the correct solution appeared often in the training set, so LLMs are likely to reproduce that.
Words describing a problem similar to the monty hall problem are going to be less common, and probably have a lot of discussion about whether they accurately match the monty hall problem, and disagreement about what the right answer is. LLMs will confabulate something that looks like a plausible answer based on the language used in those discussions, because that's how they work. Whether they get a right answer is probably going to be much more up to chance.
Edit: no it's black history month... Kinda strange
https://workspaceupdates.googleblog.com/
You evaluate features and updating training materials from what is documented here and in online help, together with any testing you want to do using free consumer accounts which you can obviously create at any time.
What I'm saying is, from what I can see in the admin portal, there's no place for me to go today to enable Gemini for my users. Things are routinely weeks or months delayed before they even become available to enable for Workspace tenants, and often times features just never get offered.
An AI system that produces right answers 90% of the time but 10% of the time drives your car into a lane divider, or says "there are 4 US states that start with 'K'" or "Napoleon was defeated at the Battle of Gettysburg" is worse than useless: It's dangerous.
As long as we call it a bullshit parlor trick, no problem. But unfortunately people are making important decisions based on these things.
Edit: My bad didn't read the parent comment properly
No way. Definitely too high once you remove their system prompts.
> In one year they have 12T tokens, while their original training set for GPT-4 was rumored to be 13T tokens.
This sounds great for understanding use, but the quality to train on seems terrible.
https://chat.openai.com/share/040ac123-c690-4274-8216-6ae091...
Way back when GPT was just fresh on the scene I had terrible anxiety about "what is the point of my whole career or even learning any more" but these days I'm much less concerned. I'll ask it something relatively simple, like "make a sentence out of words 'a', 'b', & 'c'" for it to reply with "'a' 'b' 'd' 'e'" for me to then correct it with "oh, you didn't use c" for it to then respond "sorry, here - 'a', 'c', 'd', 'f'" etc.
Definitely an amazing complimentary tool but when they say "can make mistakes, check important..." that's essential.
I haven't seen anything about this in the public , but I imagine this will also be called Gemini, just as Gemini-integration in other products is simply being called Gemini.
If you are confused about subscriptions, here's another breakdown:
Basic: $2/month for 100 GB
Standard: $3/month for 200 GB
Premium: $10/month for 2 TB
AI Premium: $20/month for 2 TB + Gemini Advanced (Gemini Ultra chatbot)
English isn't everyone's first language. I'm fairly certain you've butchered spellings of Nouns originating in other languages.
Gemini means "The Twins", but why such name ?
> write a powershell script to crawl an entire website and download all images
It still refuses to generate code for that.
Pretty hilarious thinking they can rival ChatGPT pricing with a product that doesn't approach it's capabilities.
From Jeff Dean's Twitter:
>Gemini is Latin for "twins".
>The Gemini effort came about because we had different teams working on language modeling, and we knew we wanted to start to work together. The twins are the folks in the legacy Brain team (many from the PaLM/PaLM-2 effort) and the legacy DeepMind team (many from the Chinchilla effort) that started to work together on the ambitious multimodal model project we called Gemini, eventually joined by many people from all across Google. Gemini was also was the Nasa project that was the bridge to the moon between the Mercury and Apollo programs.
The Decoder article - https://the-decoder.com/how-googles-gemini-ai-model-got-its-...
Jeff Dean's Twitter Post - https://twitter.com/JeffDean/status/1733580264859926941
I think you're reading too much into what a twin is. It's not a copy! Real-life twins ask each other questions all the time, because just because one of them learns something doesn't mean the other one automatically learns it too via mind-meld.
The only thing that was stupid with Microsoft's naming was this latest generation that they call it Series S and Series X, which is bad for 2 reasons:
- No one knows what to call them as a general term. You can say "this game is for PS5" but for them it's like "this game is for Xbox Series"? I guess they just want you to call it "Xbox" cause that's all it says at the top of the game cases now.
- They just came from selling the One S and One X, which was a mid-lifespan hardware update, the S being a smaller formfactor Xbox One and the X being a spec bump. Confusing that they continue to sell and S and an X but it's a whole new console.
They should have already learned from Nintendo who made this mistake several times with the 3DS (which many didn't realize was an entirely new but backwards compatible system from the DS), new 3DS (yes that was an actual system's name that had exclusive games that couldn't be played on the normal 3DS), and Wii U (which everyone thought was a tablet controller for the Wii)
Xbox -> Xbox 360 -> Xbox One -> Xbox Series (?). I still don't know whether S or X is the "good one". Compare it to Playstation: PS1 -> PS2 -> PS3 -> PS4 -> PS5. The upgraded line is "PS $number Pro".
Someone can tell me they have a PS5 Pro, and I know what they mean. They could tell me they want a PS6 and I know what they mean, even if the PS6 hasn't even been announced yet.
Someone tells me they have an Xbox One X and my eyes glaze over. Prior to now, that means nothing to me. I don't know when the Xbox One came out, I don't know if it's their newest line, I don't know if X is the Pro or if it's the budget. The S and X may not even indicate pro and budget, but I think they do.
At least Nintendo's names are kind of cute. It's still silly, but at least Wii or Switch is kind of endearing. Xbox Series X sounds like they let an edgy teenager name it; having X on both ends reminds me of the days of xX420ShadowRanger69Xx usernames. Also doesn't make a clean acronym; XSX is both hard to say and makes me think more of SXSW than Xbox.
Those were not the ones I called out as bad. Those are good because when they came out they were unique and memorable.
Let me list out the following consoles:
Nintendo DS
Nintendo DS lite
Nintendo DSi
Nintendo DSi XL
Nintendo 3DS
Nintendo 3DS XL
Nintendo 2DS
New Nintendo 3DS
New Nintendo 3DS XL
New Nintendo 2DS XL
There's technically only 2 generations of Nintendo consoles in there, but the DSi had some exclusive physical games that were sold in store, and couldn't be played on the DS. And the new 3DS had some games that couldn't be played on the original 3DS.
The S naming has been consistent since the 360: it's the small one.
It's not a stretch of anyone's imagination that the other one is the bigger one (I mean that's t-shirt sizing), nor that it exists in the same generation as the S and therefore is not bigger just for the sake of taking more real estate under the TV.
The one they nailed though is Xbox One X, which is recursive.
1. Completely stops hallucinating, since we can demand it to internally prove its claims before showing the answer;
2. Stops outputting incorrect code (for the same reason);
3. Starts being capable of outputting complete projects (since it will now be able to compose pieces into a larger code);
4. This is also what is needed for an AI to start self-improving (as it will now be able to construct better architectures, in a loop).
That's why I argue getting the AI competent in logical reasoning is the most important priority, and we'll have no AGI until it does. After all, humans are perfectly capable of learning how to use a proof assistant.
Moreover, if an AI can't learn it no matter how hard it tries, you can argue that there is at least one human capability that the AI can't replicate, thus it isn't an AGI.
> We are not talking here about the rain he brings on each time exercises his vocal cords, but rather about the prevailing atmosphere in the village: when it is time to party, when wild boar are roasting on the spit, you can be sure to find Cacofonix tied hand and feet with a gag in his mouth.
WTF? Do people normally think about words in this way, utterly divorced from their meaning?
If there are these "Feelings" around these words, how is any sentence correctly taken at face value. How does one communicate to these people the direct and correct meaning of the terms used.
For example, sentence sounds like seance, do they feel like i'm asking the spirits of the dead ?
Correct sounds like wrecked, do they assume that everything is broken in the above sentence.
Is communication with fraught with unknown minefields of unintended emotions and misundestandings ?
Well, it is one. I wish they'd choose a slightly more unique name but camping on well-known words is a beloved tech tradition.
(f (g (h (g z))))
((((1 * 2) + 5) * 2) * 3) = ... not 17?
Or, again, am I missing something?
Is it not ironic that the supposedly test of AGI is flawed and its human designer fail to see it and denied it when presented with facts. Maybe the test designer is hallucinating just as much as those LLM? :)
And like I said, there's plenty of stuff that's only available in paid Workspace. A lot of business features live there. (While things that are meant only for personal consumers aren't there.)
I'd rather have it defaulted to off with the ability to turn it on for selected OUs, so I can trial it out and create my own documentation around it. But instead, I have to wait often weeks or months for features to become available to even turn on for my tenant. Users are like "hey I heard this awesome feature, can you turn it on?" Nope!
Can you quantify your assesment with a few examples?
> Choose your preferred AI model from GPT-4, Claude 2.1, Gemini, or Perplexity in Settings. Easily switch models for better answers.
I'm just trying to work out if there's any reason at all not to objectively prefer it to ChatGPT Plus, since it has GPT4 + other models. But does it not do image generation? And I don't know if there's mobile apps (sure I could check the relevant stores, but I'd expect to find it on the website - verifies it is actually an official app not a scam apart from anything else).
Edit: ok, answered on Reddit - https://www.reddit.com/r/perplexity_ai/comments/18eqmig/how_... (nice, it is possible as of December); and via DDG (not linked anywhere on the site?) - https://perplexity.ai/android (nice, there are mobile apps)
Although it doesn't seem very well integrated:
> I'm an AI text-based assistant and I'm unable to generate images. However, I can help you visualize the scene with a description. [...]
and then it appears on the side: '[PRO] Generate image' as described on Reddit. Presumably the nonsense about not being able to generate an image will still be there if I had pro, I just would be able to click that side button and have it then generate one.
Where it really excels is finding answers to questions and follow ups. It uses ChatGPT to summarise the results, and provides links.
Essentially, finding a use for chat ai rather than an inane discussion.
I can't justify two of this kind of thing at ~$20pcm to myself, but I do find it useful enough to pay for one I think.
(ChatGPT at the moment, I was considering Perplexity, but would miss images & ChatGPT's jupyter notebook integration. Maybe I just need to find some open source or roll my own that does just enough for me with the API, probably cheaper than Plus too..)
The iPhone is literally just iPhone <Number> with Pro for high end, or no modifier for low end. Add “max” for big screen. The only confusion maybe is “max” isn’t obviously referring to screen size.
iPhone 15, 15 Pro, 15 max, iPhone 15 Pro Max.
Macs are the same way. I don’t think it’s fair to say it’s confusing that “M3” processor has different specs than “M2” processor.
Beyond that, Mac laptops are Pro vs Air, defining how powerful vs portable they are with associated screen size variant 14, 16 and 13,15.
MagSafe means two different products.
The current MacBook Air is thicker than an older MacBook.
I’m not even sure what a “pro” phone is, but okay.
The iPad lineup has been a total mess for years.
I’m not saying these names are impossible to decipher, but they do require some research.
I see your point, I do agree that the name of their processors were too marketing team driven.
> The current MacBook Air is thicker than an older MacBook.
The current air is plenty thin to be called “air”, and they haven’t made a “MacBook” since like 2016. It’s not confusing here IMO.
> I’m not even sure what a “pro” phone is, but okay.
It’s the line with overall better specs. The last 20 years of tech products have solidified this definition is. Not a new concept.
> The iPad lineup has been a total mess for years
Yes this is absolutely embarrassing for them. I presume they have some BS market segmentation reasoning. Looking at their website, I can probably explain the target market for each one, but it’s still a disaster. They should dramatically redo it, and designate the really cheap one as “iPad for education” to totally segment it out, so it can be “iPad small screen, medium screen, large screen, and iPad with Mac processor and pro tier features”
> The current MacBook Air is thicker than an older MacBook
I feel like you’re just looking for things to be mad about here; it’s thinner than _current_ MacBooks.
> I’m not even sure what a “pro” phone is, but okay
Okay this is just ridiculous. It seems you would be unhappy with any naming convention other than “iPhone Good”, “iPhone Better”, and “iPhone Best”.
it's actually 15 Plus rather than 15 Max, which i'm sure you now see is a bit confusing
I've talked to many of HN's Google Docs jockey founders that genuinely didn't realize 85% of the US domestic business market is in M365. And they further don't realize that "Continue with Microsoft" is dirt simple and lets companies offer company-managed logins to your SaaS without all the AD/SCIM/SAML nonsense.
"But everyone has Gmail." Well, no, that's not how companies work. And if you think everyone's in Google, that's fine, your login page should look like one of these:
https://www.xsplit.com/user/auth
https://id.atlassian.com/login
You don't even need the "continue with SSO" if you do the Atlassian practice of letting a firm "claim" the domain part of an email and using that to redirect to an SSO flow. And to start, skip SSO, and just use the "Continue with" Oauth2.
Globally, Google brand is 10x stronger than Microsoft for Small Businesses
It's not a bubble when one specifically names the Venn diagram circle "85% of the US domestic business market". It's naming a market.
> brand is stronger
Presumably the founders' interest is wallet share, not market share.
Are you saying Atlassian is in a US bubble?
1. Real estate - Youtube, Gmail, Maps, Search (for now), etc. 2. Compute - probably still the best in the industry, but with recent Microsoft/meta compute buys it's hard to say for sure. 3. Talent - probably also still the top of the industry. Geoff Hinton and Zoubin Gharamani setting direction and Jeff Dean building it is hard to beat, and the ranks are deep. Yann LeCunn is also brilliant and Andrej Karpathy while less seasoned is one of the top researchers in the field, but overall there's still a bit of a spread from Google's roster, at least when it comes to AI researchers.
If Sundar and the other top brass weren't MBA-bots with no vision, and the famous Google bureaucracy had been reigned in gradually over the last 5 years while promoting a builder-centric culture, this would be in the bag for Google no question. Instead, Satya Nadella played 3D chess while Sundar was looking at a checkers board.
Google killed the culture and is bleeding top talent. They have reduced themselves to digital landlord and sure they can extract rent, but that’s not what attracts people.
Google's 'don't be evil' grad-school-style culture had fallen apart by the late 2010's because there are tons of people who will just rest and vest.
So strong ML researchers basically were creating massive value but much of it was going to rest&vest salaries. OAI basically came along and said - hey, we don't have rest & vesters, do you want to make $1m+/yr? And most of the top google researchers said yes.
and not "cherries" and "pears" like the example found on the internet.
Do LLMs have logical rules built in? What makes them different to a very advanced Markov chain?
Are there any models out there that start from logical principles and train on top of that?
(Apologies for poor understanding of the field)
I thought of this question after coming across this exact scenario as I walked up to a glass door.
It’s not some pretend scenario. Often, when you approach a glass door, there is writing intended for the person on the other side, which appears to you as mirror writing.
I wondered if chat gpt could figure that out, and to my great surprise it could. That to me formed a new benchmark in my mind of how much of a world model it must have to figure that out.
Some of them I don't mind too much. The XL and Lite SKUs make sense to me, presuming they mean what they appear to.
3DS makes intuitive sense to me, it's clever.
There's a separate conversation to be had about whether it's too many SKUs (probably) but name-wise I only really hate "New Nintendo" and DSi. DSi only because it's far less intuitive than the others.
so far it's a close race between philosophers and mathematicians. I'll take your comment as a vote in favor of mathematicians
Of tangential interest: I recently heard that Faraday, while discovering new electromagnetic phenomenon, then turned to either a linguist or classicist for help in assigning/inventing terms for them. (I cannot find a link for this just now, so consider this heresay.)
another cultural difference is the kind of homework they hand out; the difference boils down to whether you hand over a printed (or printable) proof checked by reading through it, or a runnable program or script checked by running it
It's a little scary that it can be so hard to evaluate the correctness of these LLMs even when we are paying close attention and looking for mistakes. Or maybe the scary part is that we can become biased when we want to believe.
agi may as well be God, the bars some people have.
Isn't that (h(g(h z)))?
And, FWIW, at least in my test, Gemini gets that in its final answer, though it failed in the two other drafts:
https://g.co/gemini/share/c922e7ef62aa
ChatGPT sputters:
https://chat.openai.com/share/25abbf47-2ed4-4635-a351-90a9a6...
(ETA more Gemini testing suggests its correct answer was a one-off)
Edit: Not native. I'm not sure 'rules of engagement' is the correct english term here.
Thank you for the explanation. It seems like the LLM "plays" to learn? That's very cool, thank you again.
Handcrafted by humans ? No
But it's still possible to learn such rules from the data in an effort to complete the primary objective (predicting the next token)
Really nothing. There's some feedback structure in the layers of the model, it's not just one big probability table. But the technique is fundamentally the same, it's Markov, just with the whole conversation as input and with billions of parameters.
so while written philosophy is verbose, philosophers talking can "transfer" a lot of "meaning" with short sentence
whereas mathematicians will likely need to talk for a very long time for what they can write down in a short terse equation
> something containing or consisting of two matching or corresponding parts.
If we were talking about the word "twins" in the abstract, the broader definition might make sense. But we aren't — we're talking about Gemini. If that conjures up general notions of "matched-ness" for you, that's great. When I think about Gemini, I think about mythological twins. I don't think about corresponding parts that complement each other.
For a product name to be successful, it should appeal to a wide range of people. If I'm way out in left field on this one, perhaps they've found a great name. But I would point out that my comment, which is critical of the name change, is the very first comment in the entire thread. I would take that as evidence that most people don't see the name and think "oh, it's like complementary items, like my brain and the AI".
To be clear, I was shocked to see this comment above all substantive discussion of the new release. I would have thought it would have been buried under examples of ways in which Ultra is better/worse than some other LLM.
But touché - many of the critiques are being written by super talented and impactful people. But I do not think those critiques are necessarily incompatible with what I am saying.
There is a very real and very frustrating (if you work there and want to be impactful) phenomenon in these tech companies of people resting on their laurels.
In some ways, this is proof that Gemini isn't cheating... It is just doing typical LLM hallucination
iPad 10 is still A14 Bionic, not Apple Silicon.
The iPad Mini has A15 Bionic.
Honestly, Google is called "Google". ChatGPT is called "ChatGPT". Maybe it'll be a joke, maybe people won't think about what they're calling it after 30 seconds.
This conversation is taking itself a bit too seriously for what's drifting into Pepsi logo gravitational pull territory, though.
> But I would point out that my comment, which is critical of the name change, is the very first comment in the entire thread.
Sure. Everyone has an opinion on what color the bike shed should be, too.
That said, the places I've worked where there was a shared belief in the importance of our work were exhilarating. But, the way they achieved that was essentially by getting rid of bullshit. You know, no one's building their own web framework or writing their own in-house query language (you know, unless you really have to). No one's spending an hour of everyone's time figuring out what to name this class.
I think we haven't figured out how to keep that energy once you build a company big enough that's got something to lose. Suddenly it totally feels worth it to have a meeting about changing the shade of blue in the logo from this to that, because what if revenue declines 0.1% and that's $40m and then layoffs? One of the amazing things about Google was that it somehow seemed to keep that energy well into becoming a tech behemoth; it felt like they defied gravity, like their commitment to not doing evil and open web standards--or maybe we thought the web itself had ended evil corporations like Microsoft forever and Google was its avatar--had allowed it to overcome this corporate version of Fermi's paradox.
Whatever. Maybe this is just a bunch of word salad haha. All I'm saying is it takes two to tango, and just like I'm sure there's a non-zero level of personal culpability responsible for this phenomenon, I'm sure there's a non-zero level of systemic and cultural cause too.
Edit: Indonesia is the largest market which has Google beat Microsoft (https://www.statista.com/outlook/tmo/software/productivity-s...). India (due to Zoho) and China (due to... locally-specific software like Kingsoft (aka WPS) et al.) took a large chunk but on Microsoft-Google tussle MS still beats Google (especially in China where Google doesn't really operate).
The Apple TV hardware and the Apple TV app on your iDevice can both be used without paying a subscription. The hardware has all other streaming apps a la Roku, and both it and the app on your iPhone can be used to purchase and watch TV shows and movies.
Hangouts, Allo, Duo, Buzz, Google Talk, GChat, Inbox, Messenger, Messages, Bard, Gemini, etc. Who else has a track record of chopping and changing like this?
Apple TV (app) gives access to Apple TV+ (streaming service)
- AppleTV - the all things tv stuff from Apple that I pay once for
- AppleTV+ - all things tv stuff from Apple that I have to pay every month for
I guess the + is like the + sign on a calculator ;)
It's an industry term now.
Google+ was too far ahead of its time!
To you. You are projecting.
https://en.wikipedia.org/wiki/Disney%2B "Disney+ was launched on November 12, 2019"
https://en.wikipedia.org/wiki/ICloud "In June 2021, Apple introduced iCloud+..."
https://en.wikipedia.org/wiki/Fitness_(Apple) "Apple Fitness+ is an ad-free video on demand guided workout streaming service announced during Apple's September 2020 Special Event"
I’ve always associated “plus” with Apple, not with Disney.