Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Leverage of LLMs for Individuals

mazzzystar.github.io

Post reply on HN
Print view View original

251–260 of 311 posts

Re: The Leverage of LLMs for Individuals

#251

Post by esafak »

croes wrote: post #176

I wonder if this is really a benefit for learning something. A teacher who tells you the right answers doesn't sound like a good teacher. In hindsight I learned the most from my mistakes and the errors I'm to fix over longer period of time. Sometimes these failures were of use in later projects. I missing all this from GPT. It doesn't really sound like learning more like cheating.

You don't need to understand every problem you encounter. Some things are just an obstacle to be overcome any way possible. Pick your battles.

Re: The Leverage of LLMs for Individuals

#252

Post by esafak »

croes wrote: post #174
senko wrote: post #102

> Current documentation is written for human reading, with a mix of text and code blocks that makes copying a poor experience. Perhaps soon, documentation and APIs will become GPT-friendly first. Yes. I have recently annotated my Pydantic models and fields with the explicit intention to use the resulting JSONSchema to inform GPT how to structure some information (in effect, writing a one-off client for an internal AP…

I thought the point of GPT is to be human like and not that humans adapt to GPT.

Humans are limited in their language too, so that's still human :) It's just that you're surrounded by humans who speak your language.

Re: The Leverage of LLMs for Individuals

#253

Post by ekanes »

Ethan_Mick wrote: post #242
martinflack wrote: post #183

Earlier quoted context omitted.

Given the token count limits on input and output, I've been wondering how folks work on these long-running projects? Is it just not a problem, or are there some tactics? I find in trying to build up lengthy outputs that it starts truncating or leaving out things from way before.

I think this is a good question. Screenshots are hard on HN, but I could write up a blog post about it all once I have a demo of the game. I've been using ChatGPT and GPT-4 since they came out, so I'm pretty aware of their limitations. You can't build an entire project in a single project. GPT loses the context at one point. With that in mind, break down the project into chunks and make each one a conversation. For m…

Super useful, thanks for writing this up. I bet a short blog post with screenshots would go over great.

Re: The Leverage of LLMs for Individuals

#254

Post by drbawb »

gexla wrote: post #59
geek_at wrote: post #7

Learning something with GTP-4 is so much more fun than using google/Stack Overflow. It's like having a tutor that knows your code and gives you hints and solutions based on your actual project. It's a real game changer for learning

And this is what you might say while you're learning. As you gain more experience, you realize that there's a wide range of solutions with some spectrum of a fit to your situation. A given solution may fall down in certain cases. What I love you Stack Overflow, is the context which comes with it. You get replies on a given proposed solution which point out where the solution may fail.

>you realize that there's a wide range of solutions with some spectrum of a fit to your situation

I ran into this the other day and it's made me very leery about using chatGPT for learning things I don't already know. I moved on from toy examples and tried getting it to write a program in a domain I was already intimately familiar with: I immediately realized that this thing is going to help people churn out all sorts of code that is a poor fit for the surrounding system or ecosystem.

Basically I had it write a program in Elixir as a GenServer. After that was done I asked it how I could integrate that solution into a Phoenix web application. I had to hold chatGPT's hand, so to speak, as we evolved the solution from:

(1) Spawning (and linking!) the GenServer to a controller i.e. in response to a web request.

(2) Spawning and linking the GenServer to the application but outside the supervision tree.

(3) Spawning the GenServer inside a supervision tree.

Now technically the application could have worked, more or less, if you ran it at any one of those intermediate steps. However only the last solution is the robust and idiomatic one. It felt almost like a constraint solver to me: we iteratively arrived at the right answer by adding more and more constraints to the solution. The problem, as it relates to a novice, is that they don't have a list of constraints rattling around in their head. (Language idioms, best practices, framework knowledge, system architecture knowledge, etc.)

The insidious thing here is that 1 or 2 are syntactically valid programs. If you try to beat 1 and 2 into submission you're going to have a subtly broken system, one that makes a lot of Elixir programmers very sad.

---

I'll be watching the Khan Academy guys pretty closely, because they seem to have put a lot of thought into how students could use these systems safely and effectively.[1] I think the answer is going to be we need AIs that are aimed at professionals, and AIs that are aimed at education. The hard part will be that somehow we need to direct people to use one appropriate to their skill level.

[1]: https://www.ted.com/talks/sal_khan_how_ai_could_save_not_des...

Re: The Leverage of LLMs for Individuals

#255

Post by ilaksh »

zackmorris wrote: post #234

Semi-serious question: how do we help those too old to begin the training? When I went through profound burnout in 2019, the part of my brain that handles planning and execution shut down for about 6 months. I could barely get out of bed, brush my teeth, etc. The grieving process was rough, as well as the struggle to relearn how to function in a culture that doesn't allow breaks. And it was physical, perhaps brought…

It _is_ a "dog-eat-dog" world and AI _should_ make it possible to "raise all boats". For that to be possible then we need new paradigms for society. It's very difficult but AI should also help us move in that direction.

As far as your particular problems, I hope you find the help you need. It sounds like you may have depression and/or some other psychological issues, but I'm not a doctor. The way I see it is that these types of opportunities in VR or AI have not actually passed by.

Re: The Leverage of LLMs for Individuals

#256

Post by ilaksh »

nice_byte wrote: post #245
valine wrote: post #70

Earlier quoted context omitted.

This sounds to me like you have no idea how to properly integrate LLMs into your workflow. Just because they’re not useful for changing large code bases doesn’t mean they can’t be valuable. A few examples of things I’ve used LLMs for: Writing bash scripts to automate various parts my workflow Quickly interpreting complex regex Tutoring me on how to use poorly documented APIs Proof reading important emails Everything…

> Tutoring me on how to use poorly documented APIs Good luck with that. GPT-4 is _incredibly_ bad at Metal (most under-documented GPU api I've ever worked with), but more importantly it's _even worse_ at Vulkan, which is complete opposite - it's meticulously documented. The stuff LLMs are good at is the stuff that a lot of people use and talk about all the time, in public. There's just not a lot of public discussion…

It has an 8kb (or 32kb if you are lucky) context. Try giving it the relevant documentation examples before asking a question.

Re: The Leverage of LLMs for Individuals

#257

Post by ilaksh »

esafak wrote: post #249
collaborative wrote: post #139

Earlier quoted context omitted.

Also got a couple decades, a ChatGPT Plus subscription on top of running my own local instance of Vicuna and access to Bard. Enjoy it while it lasts. The training set (Stack Overflow) will dry as people move away from it, resulting in model degradation, resulting in not having a useful AI AND not having a useful SO I admit to using AI, but only for what I was using SO before. Which is 0% of the work I actually get pa…

I'll be really impressed the day models can generate code by just grokking the language spec and documentation.

It can do that now. Has an 8kb (or 32kb) context. You might need to do a bit of work preparing a concise description and language examples.

Re: The Leverage of LLMs for Individuals

#258

Post by ghaff »

SuoDuanDao wrote: post #114
ghaff wrote: post #61

Earlier quoted context omitted.

Assuming it actually happens, how different is it from a ton of other things? Hpw many rote sysadmin or paralegal tasks of 20 years ago still need basically a warm body to do them?

Fewer, I'd assume? What I'm curious about is whether anyone has advice for people getting into programming now.

I doubt anyone has a clear enough crystal ball to give confident, actionable advice. Obviously AI, among many other things, erodes the value of most easy to acquire knowledge skills at the low end. But that kind of thing is constantly being eroded all the time and while uplevel/upskill is generally good advise, it's hardly unique to AI. Nor is there evidence yet that computer programming/software engineering is going to be uniquely impacted by these new technologies.

Content farms and other low-end writing almost certainly will be impacted significantly. But that was mostly not a good place to be anyway. Writing generally isn't a good bet unless it's effectively in support of something else that pays the bills or you get very lucky.

Re: The Leverage of LLMs for Individuals

#259

Post by a_brawling_boo »

Ethan_Mick wrote: post #67

> More importantly, it gives me the courage to dream and attempt things beyond my current abilities. This is one of the small things that GPT has pushed me to do. I'm an experienced programmer and grew up playing video games, but I am not a game developer. I've dabbled over the years but can't build anything outside of a tutorial. The other day, using GPT I went through and made a Pixel Dungeon clone using Phaser (Ja…

I am software engineer and I have certainly attempted use GPT for coding with mixed results.

But what I am really impressed using it for writing. I am writing the story of my abusive upbringing with a mental ill mother. I am not a writer, but this thing is awesome because I can ask it to give me prompts and it is jogging my memory more and more then I can give it rough outlines and thoughts and it will organize it into more of a literary style, then I can go through and update most of the wording to my own liking or leave as is as I see fit. I am easily able to produce much more and a better quality than without it.

Re: The Leverage of LLMs for Individuals

#260

Post by efields »

zackmorris wrote: post #234

Semi-serious question: how do we help those too old to begin the training? When I went through profound burnout in 2019, the part of my brain that handles planning and execution shut down for about 6 months. I could barely get out of bed, brush my teeth, etc. The grieving process was rough, as well as the struggle to relearn how to function in a culture that doesn't allow breaks. And it was physical, perhaps brought…

I feel your struggle. I can relate to it. I think I've gotten by in a way bc of the support systems around me, but I don't think any of them know just how much my relationship to work has changed since around 2020 or so.

If you're able to think and type this profoundly, you, personally, are not too old to contribute to something that motivates you. I haven't found that yet, but I haven't given up hope yet either.

Post reply on HN