GPT Store Launch

85 points by atomon 2 years ago | 65 comments

Just got this email from OpenAI:

Subject: GPT Store Launch

Dear GPT Builder,

We want to let you know that we will launch the GPT Store next week. If you’re interested in sharing your GPT in the store, you’ll need to:

- Review our updated usage policies and GPT brand guidelines to ensure that your GPT is compliant

- Verify your Builder Profile (settings > builder profile > enable your name or a verified website)

- Publish your GPT as ‘Public’ (GPT’s with ‘Anyone with a link’ selected will not be shown in the store)

Thank you for investing time to build a GPT.

- ChatGPT Team

ianbicking 2 years ago |

I'm sure there will be improvements, but making a custom GPT a few weeks ago I was very unimpressed:

1. The GPT builder itself didn't feel like it was a well-tuned prompt (i.e., the prompt they use to guide prompt creation). It created long-winded prompts that left out information and didn't pay attention to what I said. Anything I enter into the GPT builder interface is probably very important!

2. The quotas are fairly low, and apply to testing. I was only able to do maybe 10 minutes of playtesting before I ran out of quota.

3. There's no tools to help with testing, it's all just vibes. No prompt comparisons.

4. The implied RAG is entirely opaque. You can upload documents, and I guess they get used...? But how? The best I could figure out was to put text into the prompt telling GPT to be very open about how it used documents, then basically ask it questions to see if it understood the content and purpose of the documents I uploaded.

5. There's no extended interface outside of the intro questions. No way to emit buttons or choices, just the ever-present text field.

6. There's no hidden state. I don't particularly want impossible-to-see state, but a powerful technique is to get GPT to make plans or internal notes as it responds. These are very confusing when presented in the chat itself. In applications I often use tags like <plan>...</plan> to mark these, which is compatible with the simple data model of a chat.

7. There's no context management. Like hidden state, I'd like to be able to mark things as "sticky"; things that should be prioritized when the context outgrows the context window.

These are all fixable, though I worry that OpenAI's confidence in AI maximalism will keep them from making hard features and instead they just rely on GPT "getting smarter" and magically not needing real features.

jasonjmcghee 2 years ago | |

Re: 1. I've made many GPTs and never took the time to read that first page / use the GPT builder. I always immediately jumped into "Configure". Had no idea this was a thing.

Re: 2. 100%. It's rough.

Re: 4. Had a ton of issues where it would just error and say it couldn't find the document, completely ruined the point / purpose of one I made.

Re: Hidden state - could be fun, but I do like the transparency of everything needing to be out in the open. But maybe a "hidden by default" scratchpad.

pona-a 2 years ago | |

Maybe you can hack some context management and hidden state with custom functions? The scratch buffer can literally be an endpoint that returns OK and has a field like "plain: list[str]", assuming it keeps function call data in memory. Better context memory can be done perhaps by reminding in the system prompt to always call getPinned() each 5 messages, perhaps...

But yes, the whole thing does seem bound to regress to low-quality "I'll enter 1/5th of your request in for you". You can probably even make a script that uses GPT-3.5 to generate these "GPTs".

ianbicking 2 years ago | | |

Yeah, you can definitely do a lot with Actions, and I've seen some examples of that. But if I want to deploy a service then I'd rather make a nice frontend along with it, and Custom GPTs aren't that! (But the fact I don't have to monetize just to support OpenAI API costs is still very appealing.)

At the moment Actions are pretty brutal to the experience, with constant confirmations and they seem to halve both the speed and the quota since I think it takes two GPT responses, one to assemble the Action and another to react to the result. Using a Custom GPT that uses extensive actions means sitting and watching it think, waiting to hit a button, then sitting and watching it think for a long time, only to run out of quota before you get to anything interesting.

qingcharles 2 years ago | |

I use several custom GPTs that I built inside GPT Pro and they have doubled my productivity over using GPT alone, which had already doubled my productivity.

Every time I get a response that is off from the custom then I give it a nudge to edit its configuration. The main issue is that its configuration doesn't have enough space for all the rules and it likes to ditch more minor rules when you give it something extra to remember.

esjeon 2 years ago |

I might be overthinking, but this "store" thing would not work that well. I blame GPT here, because I'm quite certain that GPT itself can be used to analyze and clone GPT apps, perhaps fully automatically. Even those extra knowledge added by app developers would get extracted through jailbreak, which also can be automated. The store will end up being littered with auto-generated clones.

replwoacause 2 years ago |

Anybody else having issues with the app on iOS where the model changes from 4 to 3.5 after the first response? As a paid user, it’s very frustrating to have my preferences overridden and the quality of 3.5 answers is comparatively lower. In fact almost so poor as to be useless, so the mobile app is currently unusable.

debian3 2 years ago | |

Mine stay on v4

lysecret 2 years ago |

My bet was they would delay it. Well excited to see what people will build but also a little worried. Users have developed a lot of trust towards ChatGPT some are using it as a therapist, uploading a lot of secret info etc.

Now with custom gpts anyone can piggyback on that trust and just upload all that data to their servers.

drakonka 2 years ago | |

> Now with custom gpts anyone can piggyback on that trust and just upload all that data to their servers.

Can they? I thought custom GPTs were hosted entirely by OpenAI with no middle-man in-between? How would the creator of a custom GPT receive any user prompt data? AFAIK they're not even accessible through the API to build on top of (unlike the Assistants)

_boffin_ 2 years ago | | |

They're able to utilize APIs

ilaksh 2 years ago | |

Why would you make that prediction when they just sent an email that says it's launching next week?

ilaksh 2 years ago |

What I'm wondering is how do we get paid and what kind of cut are they taking? I'm a little worried it's going to be like, "and creators can earn up to 20% usage credits depending on the number of installs their GPTs get!"

jasonjmcghee 2 years ago | |

In its current state, idk how payment can possibly work on non-api driven GPTs, honestly - other than a tip jar. You can easily get it to print out the prompt and return the full text of documents. Even easier to do a close approximation of the above.

mattbrewsbytes 2 years ago |

Is this a directory of people that have built something using OpenAI's API's? What exactly is being sold here if this is a store?

Sorry, I haven't been doing much in the AI space other than an occasional Ask GPT question once in a while.

CharlesW 2 years ago | |

This should answer your question: https://openai.com/blog/introducing-gpts

We’re rolling out custom versions of ChatGPT that you can create for a specific purpose—called GPTs. GPTs are a new way for anyone to create a tailored version of ChatGPT to be more helpful in their daily life, at specific tasks, at work, or at home—and then share that creation with others.

Starting today, you can create GPTs and share them publicly. Later this month, we’re launching the GPT Store, featuring creations by verified builders. Once in the store, GPTs become searchable and may climb the leaderboards. We will also spotlight the most useful and delightful GPTs we come across in categories like productivity, education, and “just for fun”. In the coming months, you’ll also be able to earn money based on how many people are using your GPT.

H8crilA 2 years ago | | |

What's a version of a ChatGPT? A custom model? With custom pretraining, or just custom fine-tuning? Or just a custom prompt, lol.

mattbrewsbytes 2 years ago | | |

> you’ll also be able to earn money based on how many people are using your GPT

So how does that work? Are they showing ads? (Narrator: its always ads) Is this the new ad-sense and search engine replacement? Its not SEO anymore, its custom GPTs.

ubj 2 years ago |

I received the same email. My assumption is that all of the GPTs in the store will still require a paid ChatGPT plus plan to access, but I have no way to confirm this. Does anyone have a source verifying whether this will be the case?

CharlesW 2 years ago | |

OpenAI has suggested that your assumption is true, although I'd further assume that ChatGPT Enterprise (in addition to ChatGPT Plus) customers will have access as well. Basically, it's the Spotify model.

"In the coming months, you’ll also be able to earn money based on how many people are using your GPT." https://openai.com/blog/introducing-gpts

yosito 2 years ago |

It will be interesting to see if anyone has made any worthwhile custom GPTs. I've tried making custom GPTs and, to be frank, I found the functionality extremely basic and barely more effective than just copy/pasting a custom prompt.

neverrroot 2 years ago |

This looks like an interesting opportunity to learn something new. Anyone knows about any open source projects in this area?

minimaxir 2 years ago | |

GPTs are essentially a proprietary moat-building of several open-source workflows, most especially system prompt engineering, tool-usage, and RAG.

Unfortunately there's no magic open-source solution since there's a lot of moving pieces involved that are bespoke to a given use case, and the ones that claim to be magic are libraries like LangChain, which aren't.

eshack94 2 years ago | | |

This is the most accurate and clear-eyed take I've seen on GPTs so far. They might be useful, but they're not magic and they're intended to enhance OpenAI's moat-building operations to make it harder for people/companies to walk away from the platform amid future competition.

david_shi 2 years ago | | |

There really should be open source versions.

It's perplexing why there aren't, especially when the individual components are relatively straightforward (code interpreter, RAG, search, function calling, image generation).

next-fulcrum 2 years ago | |

It depends on what you are looking for here. If you want to build with LLMs, there are a number of open source options which can be self hosted (although they may not perform on par with GPT-4).

If you are referring to the assistants API which adds some more complex behavior, there is LangChain as others mentioned, but also some more turn key, self hosted options (which I have not tried) such as

- https://github.com/stellar-amenities/assistants

- https://github.com/transitive-bullshit/OpenOpenAI

If you are referring to the marketplace itself, most developers are currently rolling their own web apps with billing and auth while they wait for OpenAI’s offering.

Finally, as a shameless plug, I’ve been working with some friends on a marketplace which provides auth and billing but decouples you from a specific model provider and the high platform fees they may plan to charge. It isn’t open source but we think it might strike the right balance. https://market.interactwith.ai/

karmasimida 2 years ago | |

GPTs is just a glue layer. It adds some but small values on top of GPT4, emphasizing on small.

If you don’t have GPT4, no value is added

ArlenBales 2 years ago |

This close to launch and no information on how they'll audit GPTs. I just want to know their review process and how they'll enforce their usage policies, specifically regarding privacy (and GDPR compliancy).

How will they prevent a developer from sending and storing private information from their GPT to their server through APIs?

How will they prevent doxing? Such as a GPT posting hyperlinks that direct to a server owned by the developer that performs geolocation.

4ndrewl 2 years ago | |

Also, who is on the hook when your app outputs copyrighted material? https://garymarcus.substack.com/p/things-are-about-to-get-a-...

CharlesW 2 years ago | | |

They are, via their "Copyright Shield" program: https://openai.com/blog/new-models-and-developer-products-an...

drakonka 2 years ago | |

Unless they're changing this, custom GPTs as far as I know are not accessible through OpenAI's API. AFAIK they're just ChatGPT running GPT-4 with a custom instruction and optional knowledge base. No private information leaves the ChatGPT interface/OpenAI. For example, here's how I'm using a private one right now: https://liza.io/creating-a-writing-assistant-with-chatgpt-pl...

etewiah 2 years ago |

I was planning on releasing some extra features for gipeties.com, my directory of custom GPTs before the store launches. I’d better be quick now!!!

It is quite possible this will spell the end of GPTs directories but if they mess up with curation there might still be a space for them.

ChrisArchitect 2 years ago |

Tell HN:

stainablesteel 2 years ago |

chatgpt is too lame for this to work

you can't even ask it to spell words incorrectly

if you ask gpt4 to spell words incorrectly, it fusses about it. i'm commenting on the fact that the company is too stuck on appearances

Yusefmosiah 2 years ago |

The GPT Store is poised to be the biggest platform since the iOS App Store.

Reason: The GPT-4 API is too expensive for most use cases. This encourages app developers to build custom GPTs, letting their users pay $20/month for a ChatGPT Plus subscription. To provide the same service in a standalone webapp using the GPT-4 API you'd have to charge ~$50/mo for your app only, and that's if you settle for ~50-75% margins (SaaS usually has much higher margins).

By the time GPT-4 level (proprietary or open source) models proliferate and come down in price, OpenAI will have GPT-4.5/GPT-5 for $20/mo in ChatGPT Plus, and it will be tough to ask users to pay to use a subpar model.