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

241–250 of 311 posts

Re: The Leverage of LLMs for Individuals

#241

Post by Thrymr »

vemv wrote: post #40

There's a long gap from: I built a podcast search website to: Staying in any company right now is a negative return. We humans are too easily impressed by tricks, and are too willing to extrapolate them to fantasy land. GPT can certainly accomplish an impressive variety of small tasks. Whether it can build large-scale systems that will power tomorrow's world is uncharted territory. Can you build something meaningful,…

Indeed, it is far from clear that, even if an individual can leverage the productivity gains, that individual can generate revenue from what they're doing.

Re: The Leverage of LLMs for Individuals

#242

Post by Ethan_Mick »

martinflack wrote: post #183
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…

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 me, that was:

1. Initial Setup

2. Add a randomly generated tilemap

3. Character Creation and Placement

4. Movement

5. Turn-based execution

6. Fog of War

7. Enemy Monsters

Each one of these is a separate thread. They start with:

> You are an expert game developer using Phaser 3 and TypeScript. You are going to help me create a game similar to Pixel Dungeon using those technologies.

I then copy in relevant code and design decisions we already made so it has the context. If it gets the answer totally wrong, I'll stop the generation and rephrase the question to keep things clean.

Lastly, I'll frequently ask it to talk about design first saying something like:

> We are going to start with the world map and dungeon generation to start. We'll add a character sprite and movement next. What's the best way to do tilemap generation and store the data? Don't write any code, just give me high level suggestions and your recommendation.

This lets me explore the problem space first, decide on an approach, and then execute it. I'll also ask for library suggestions to help with approaches, and I'm generally surprised by the suggestions. Like all software, once you know the design, the pattern, the goal, and have good tools to help you achieve it... the coding isn't all that hard.

Re: The Leverage of LLMs for Individuals

#243

Post by deathmonger5000 »

hansvm wrote: post #239
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 use the API and have a generic prompt prefix for each programming language and type of task to try to get as much bang for my buck with as small of a token count as possible, and then tossing in a single query with a bit of project-specific code fleshes out the rest of what I'm asking it. Prompt tokens are usually around 300-1000, leaving over 3000 for the response (which it rarely fully uses). It's garbage at pull…

Shameless plug: I created promptr to help with this.

https://github.com/ferrislucas/promptr

Edit: this PR has some examples of what’s possible https://github.com/ferrislucas/promptr/pull/38

Re: The Leverage of LLMs for Individuals

#244

Post by Ethan_Mick »

wccrawford wrote: post #235
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'm trying to visual the process you're using for this, and it's just not coming to me. Can you give me a run-down on it, or point me somewhere that has one?

Yep! I answered on another comment: https://news.ycombinator.com/item?id=35891575

I might expand on this in a blog post.

Re: The Leverage of LLMs for Individuals

#245

Post by nice_byte »

valine wrote: post #70
collaborative wrote: post #57

AI tools are absolutely useless once you get past any initial stage in a software development cycle They just can't comprehend what needs to be done even if all that's required are 2 lines of code However, we keep seeing posts from people who don't know html or how to create a chrome extension paternalizing about how we can be much more productive with AI tools. Last I heard a CEO was demanding dev increased producti…

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 (with examples) about e.g. how to properly use Vulkan in a production application, and the LLM itself can't "reason" within the framework of the detailed specification, so most things it outputs is wrong.

In the long run though, a very likely outcome is that tools that the LLMs have a poor "understanding" of just wither and die, or are relegated to being something only 3.5 people in the world use. I can see a future where literally all software is written in python just because that's the language that OpenAI's LLMs happens to know best.

Re: The Leverage of LLMs for Individuals

#246

Post by collaborative »

gfodor wrote: post #151
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…

What? You're jumping to so many conclusions here, it's absurd. You're going to have to go into research for a few years if you want to get anywhere on proving that the capability of the current systems is somehow determined by the presence of StackOverflow. Sounds like you have a very tall tower of speculative assumptions about LLMs today, LLMs in the future, the evolution of the web corpus, and other big, dynamic, a…

This is starting to sound like a debate, but I feel that the burden of proof lies more in that LLMs are anything more than a blurry representation of the data they have been trained on than otherwise. I personally don't feel like I've brought Frankenstein to life each time I load a LLM into memory..

Re: The Leverage of LLMs for Individuals

#247

Post by esafak »

lyair1 wrote: post #87

I am happy that so many people get to experience the feeling me and other software engineers feel when we write code. OpenAI democratize some of this feeling and now people that never knew how to code can experience the rush of creating something new using code. In a world where a lot of AI Researchers that develop these amazing models are slowed down by their lack of "normal" engineering skills I think it's very app…

The models AI researchers develop are cutting edge, and mathematically involved; the kind of thing I would expect an LLM to fare poorly at. And today's researchers are capable of implementing their models in pytorch and the like.

Re: The Leverage of LLMs for Individuals

#248

Post by naet »

rounakdatta wrote: post #188
boh wrote: post #113

Earlier quoted context omitted.

Despite the novelty and excitement, the profit potential for AI generated applications and content isn't particularly strong. If you can make something using AI, so can everyone else. You work at a company to make money. Using AI doesn't magically allow you to do that. If you have the ability to make a profitable company, AI may help, but it's not a business plan.

> If you can make something using AI, so can everyone else The idea / creativity is hence the key. Novel ideas don't occur to everyone.

If it's trivial to implement someone else can just take your idea and easily spin up a competitor, devaluing your idea.

Re: The Leverage of LLMs for Individuals

#249

Post by esafak »

collaborative wrote: post #139
gfodor wrote: post #100

Earlier quoted context omitted.

I’ve been programming for two decades and you’re just plain wrong here. It’s useful throughout the dev process for many things, the worst part right now is just how slow GPT-4 is to run inference. You’re probably not using it right, aren’t using GPT-4, or something. It’s a multiplier, for specific parts of development - the amount of annoying nonsense I no longer have to spend my limited time on earth thinking about…

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.

Re: The Leverage of LLMs for Individuals

#250

Post by waboremo »

appleaday1 wrote: post #107
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 like how everyone has been using ChatGPT to code in Javascript, as I have done something as well.

ChatGPT benefits from how abundant languages like Javascript and Python are. When you start diving into the lesser used languages, the struggle becomes real. Even worse if there have been substantial breaking changes in the past ~2 years.
Post reply on HN