I see claims that it makes you 7-8x more effective. That hasn't been my experience. Maybe 5-10% improvement at best. Instead of Googling myself, LLMs can sometimes give me the answer more quickly than I could find it.

Once you ask it anything not easily scraped on the internet it hallucinates like crazy and sounds so confident about it. Maybe I'm just horrible at prompting, but I can't help but feel we're still N breakthroughs away from having it really impact dev jobs.

Getting it to code, it can save me, a fairly experienced coder, quite a lot of time because it can do some boring things - boilerplate stuff, or things I can’t be bothered to look up. And I can tell if it’s done it right or not.

I’ve seen people with less coding experience use it and just take its suggestions at face value with painful results and definite detriment to their learning.

The best test I’ve seen for what it’s good at is things that are hard to do, but easy to check.

But in any knowledge economy type job, there is no ceiling on skill. Creative, curious, intelligent people who are already high skill are also going to be the most effective at using a new and weird and tricky tool in interesting ways to develop their skills.

Generative AI will make some old skill obsolete, but people who are generically good at picking up new skills will be much more effective at wielding it. Those are the same people who were good at picking up the old skills, too.

Other commenters have pointed out the difficulties users with limited domaine expertise having in parsing the output and distinguishing what is useful, novel, interesting from what is trivial or incorrect.

This slows down the iterative process of learning how to use the tool as well as refining queries because they don’t have a big enough database of ground truth knowledge to calibrate against.

That being said these can work well as educational tools to rapidly get non-experts to a point where they can participate in conversations with experts. In that regard one might say that the bulk of the value is in the non-expert users because they are far more prevalent than experts.

The biggest advantage I saw for the expert researchers was that they knew (1) which big questions to ask, and (2) how to break down those big questions into smaller, more precise questions.

I don't think the paper matches the assertion made in the title of this article - it's talking about a very specific use-case for generative AI, which won't necessarily generalize to "in all cases, workers with less experience gain the most from these tools".

I grew up without a dishwasher (when we asked our parents why we didn't have one my dad responded, "what do you mean? We have six!" referring to us kids). As an adult we have one in the house but it is rarely used. Washing dishes is a menial task but I enjoy it. It's hard to articulate exactly why. Needless to say I'm quite an experienced dish washer, there's an art to it. My process is to collect any dishes that aren't already stacked, fill the sink with just enough water, wash everything well (cutlery in first, out second last, washed individually), then wipe down all the benches and sink. I leave the dishes to drip dry. They get put away later.

When we use the washing machine I still have to do most of the steps above. Except the washing which is 40-120mins of free time for me. But then I have an extra step of checking each dish or piece of cutlery while I'm putting it away. Most things get washed well, but about 10-15% of items have food baked onto them that I then need to soak or rewash (with a more abrasive scrubber than I'd usually use). Maybe this is down to my lack of experience stacking? The whole process takes longer, but it's (arguably) lower touch and (I hear) uses less water.

Which is better? In a commercial kitchen a dishwasher for sure, efficiency at all costs.

But do we need to remove all menial tasks from our workflows? I'm not so sure.

When people claim that technology disadvantages workers it usually just reflects their prejudices about working people. So called knowledge workers like to think only they can leverage tech while the call center workers are fixed automatons. But in reality people at a lower skill ceiling have a much easier time leveling up.

ChatGPT when it works well is basically a Young Lady's Illustrated Primer (https://en.wikipedia.org/wiki/The_Diamond_Age). Giving underskilled people free access to information will always benefit them the most.

For example, for places where English isn't the first language, LLMs are widely used for content-based tasks (posts, emails, support), because waiting 10s for Bard or GPT to output something higher quality is worth their time. Perhaps these folks end up being more attuned than usual, more in harmony and sync with the LLMs?

Speaking from experience, it took a while for me to move from vim to vscode, from Javascript to Typescript. We probably prefer our silos and feel uber comfortable in existing setups.

  Start your response with "Let's work this out in a step by step way to be sure we have the right answer:" and work this out in a step by step way to be sure you have the right answer

Source: https://github.com/openai/openai-cookbook/blob/main/techniqu...

If your team can't autocomplete APIs, and if you can't run everything locally so you can step through your code with a debugger, and if you don't have good tests so you need an AI to tell when you broke something (see also profiling, telemetry, release quickly and confidently, etc) - you're going to get a million percent more mileage just doing these sort of basics correctly (and fast) vs investing in AI because the open secret is that most of engineering time is spent reading and debugging code rather than writing it. This should be table stakes but so many engineering teams (even at bigtech companies) can't do the above. So they're all signing up for copilot but they still iterate with logging statements and catch regressions in production.

1. Google replacement for simple queries. Like "how do I HTTP POST with go?". Saves like 30 seconds of browsing.

2. Google replacement for vague questions. Like "Which ingress controllers are popular and what's their strengths".

3. Procrastination eliminators. Like "I need an identifier for ..., can you suggest me some proper names?".

4. Boring tasks which could be solved with enough bash scrpipts or regexes, but with ChatGPT it's often faster.

5. Most impressive to me: "I want to format the following YAML according to the following rules: <vague imprecise rules>. Example: ....". This sometimes saves me really lots of time, because it acts like a human and able to follow imprecise instructions. I could either do it myself spending lots of time or write some formatter spending, again, lots of time.

I was never able to utilize it for "smart" tasks, like if I couldn't solve something and it solved it for me. It's not smart yet. But it's an useful tool in my toolbelt, definitely worth $20 and saves me time and sanity for some boring tasks.

However, in all cases I have seen a very substantial decline of the capabilities of chatgpt-4 with the last few releases. E.g. it used to get code snippets most often right before. Whereas now it tends to be wrong most of the time. Usually it conflates capabilities of several distict libraries, just hallucinating (extrapolating) some non existing functions or attributes.

I personally suspect they are 'cleansing' the training data, and/or driving severe 'schizophrenia' into the model through conflicting RLHF.

feels like there is a viewpoint floating around that chatgpt is valuable in part because of the RLHF work

but does this makes it generally capable? or just prove that you can hire essentially the people you would hire to staff a call center (language skills + good generalists) to create a language model that behaves essentially like a call center (refuses to take any actions that are not allowed)

I’ve been in tech 18~ years and get a lot out of copilot and chatGPT every day.

Take for example this automated help that I found only minutes ago - and seems to prove that generators can be racist (...I am joking):

https://ibb.co/v3VRTQQ

For example, we all have different weights for how much trust information we get from, e.g, Wikipedia, stackoverflow, high profile bloggers in your domain, conspiracy websites, listacles, blog-spam sites etc, marketing materal etc. If the info is on a social site, is highly upvoted? Is the info from an academic journal, arxiv.org, an academic blog, or a wordoc you downloaded from scribd [1]?

Yes, this is judging a book by it's cover, but it's a heuristic that tends to work well.

By contrast, LLMs present all information to you with the same confidence in the same homogeneous interface. There is no external context. So all your normal heuristics for judging reliability are broken. -

[1] https://xkcd.com/1301/

Also, just like getting a manual dishwashing routine figured out, dishwashers are all different and need to be learned like any tool. Understanding where pieces are, which cycles run when, which compartments open and close and even how they do it, are all important. It really is best to think of it as a tool.

Some useful videos:

https://youtu.be/_rBO8neWw04 https://youtu.be/Ll6-eGDpimU