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

71–80 of 311 posts

Re: The Leverage of LLMs for Individuals

#71

Post by twic »

plondon514 wrote: post #48
pugio wrote: post #39

Earlier quoted context omitted.

Looks very cool. I am also working heavily in this space (using AI to help learning). One minor point: In your demo, you state that "Today, almost 50% of code is written by AI, so why shouldn't you learn how to code with AI?" Citation? I thought this might be true of developers using Copilot (based on their recent publications), but even that seems a bit of a stretch. I guess you could claim this because it's so easy…

Thanks for checking it out! "Today, GitHub Copilot is behind an average of 46 percent of a developers' code across all programming languages -- and in Java, that number jumps to 61 percent." - https://visualstudiomagazine.com/articles/2023/02/15/copilot...

That post just cites an original [1] from someone at GitHub which says:

> Case in point: When we first launched GitHub Copilot for Individuals in June 2022, more than 27% of developers’ code files on average were generated by GitHub Copilot. Today, GitHub Copilot is behind an average of 46% of a developers’ code across all programming languages—and in Java, that number jumps to 61%.

I'm not sure what this means. GitHub does not have the ability to measure Copilot usage across all code written anywhere in the world, so surely it can't be that. Do they mean code generated by Copilot as a fraction of code produced by someone using an IDE with the Copilot plug-in? That number still seems high to me.

[1] https://github.blog/2023-02-14-github-copilot-now-has-a-bett...

Re: The Leverage of LLMs for Individuals

#72

Post by d_sem »

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.

The silver lining of LLMs impact on Stack Overflow may be that the platform focuses on facilitating the deeper type of problem solving you describe. My experience with Stack Overflow over the years has been mixed. Frequently users misunderstand the question, threads take weeks or months to resolve, users are called incompetent by frustrated experts, answers are indecipherable to a non expert, and sometimes toxic. ChatGPT frequently outperforms these weakpoints.

If they embrace a chatGPT interface as a first line of defense for users questions, it may improve the quality of real questions, reduce repetition, and filter through actually good and compelling questions. LLMs still need systems that encourage high quality data generation from humans to improve its model. I would like to imagine a world where there is a win-win for AI and the website we've relied on so much over the years.

Re: The Leverage of LLMs for Individuals

#73

Post by ukuina »

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…

You are expecting it to replace a senior+ dev; that is not yet reasonable.

Re: The Leverage of LLMs for Individuals

#74

Post by ukuina »

akiselev wrote: post #69
pugio wrote: post #41

Earlier quoted context omitted.

Every 3 hours. But also, if you have API access you can use the OpenAI playground to query GPT-4 as much as you want. Sure, you pay a cost (per token), but if you're willing to front the bill you can move pretty quickly.

The API rate limit is 40k tokens per minute (I’ve hit it with a personal project).

That's high enough for most users, I reckon.

Re: The Leverage of LLMs for Individuals

#75

Post by yCombLinks »

d_sem wrote: post #72
gexla wrote: post #59

Earlier quoted context omitted.

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.

The silver lining of LLMs impact on Stack Overflow may be that the platform focuses on facilitating the deeper type of problem solving you describe. My experience with Stack Overflow over the years has been mixed. Frequently users misunderstand the question, threads take weeks or months to resolve, users are called incompetent by frustrated experts, answers are indecipherable to a non expert, and sometimes toxic. Cha…

The worst is the large amount of questions that solve an unrelated problem that's specific to the single asker's use case. Question, how do you do x? Response, oh, you can y instead and avoid x. Sorry, I want to know how to x, change the question

Re: The Leverage of LLMs for Individuals

#76

Post by jonfw »

bostonsre wrote: post #33

Has anyone been able to use it to effectively build more than a green field poc? It's absolutely great for that, but it's been a little clunky when trying to iterate when the context gets too large or when trying to add stuff to am existing system.

I've been able to get it to write functions for me which I can then plug into a larger system.

As an example- I have data representing a cylinder defined like so- {radius: x, depth: y}, give me a function which takes this object and calculates the volume of the cylinder.

It is unable to understand the context to deliver a feature end to end, but if you can give it the fingerprint of a function you'd like it can implement it for you (sometimes)

Re: The Leverage of LLMs for Individuals

#77

Post by d_sem »

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 is why its important to reverse mentor executive leadership so they better understand best practice usage of LLMs.

I obsoletely see benefits of tools like ChatGPT through the entire lifecycle of a product, however not as a replacement for things like good requirement elicitation, architecture, and product market fit.

In the near future I expect companies to train models on their internal code base/documentation allowing developers to learn about available libraries, API usage etc.

Re: The Leverage of LLMs for Individuals

#78

Post by Karunamon »

jmiskovic wrote: post #45
TeMPOraL wrote: post #37

Earlier quoted context omitted.

> Someone telling you that they did something cool with ChatGPT probably means GPT 3. The confusion is that ChatGPT is using GPT-3.5 by default, but if you pay the $20/month subscription price, you can switch it over to GPT-4 (with query limits). Usually, when someone is telling you they did something really cool with ChatGPT, they're actually using GPT-4. An extra layer of confusion is the API access: GPT-3.5-turbo…

Correcting the correction of a correction: The chat interface is no longer using GPT-3.5, since May 3rd. What is the default model called? I have no idea. The release notes page [1] calls it ChatGPT model, the bottom of chat interface calls it "ChatGPT May 3 version". Also people usually call out when they use GPT-4, but in the end you can only assume and be wrong 50% of time. [1] https://help.openai.com/en/articles/…

For whatever it's worth, playing with the model selector gives you a parameter in the URL.

The default model is "text-davinci-002-render-sha"

The legacy one is "text-davinci-002-render-paid"

GPT-4 is just "GPT-4"

One other useful tell if someone is showing you a screenshot of chatGPT is that GPT-4 uses a black logo avatar, where 3.5 uses a green one.

Re: The Leverage of LLMs for Individuals

#79

Post by zoogeny »

> Perhaps soon, documentation and APIs will become GPT-friendly first.

I can imagine documentation becoming ChatGPT plugin aware. Like, the automatically generated stuff that comes out of Swagger and the like. Maybe a killer feature for a new API documentation startup?

Re: The Leverage of LLMs for Individuals

#80

Post by jstx1 »

Karunamon wrote: post #24

The confusion in terms called out here (and even demonstrated) is probably not to OpenAI's benefit and I am surprised they haven't spent more effort in trying to correct that. ChatGPT is a website that lets you do chat completion [1] against LLM models, and it exposes some extra functions like plug-ins if you are lucky enough to be white listed for them. GPT 3.5 and GPT 4 are the actual models. Someone telling you th…

ChatGPT is more than an interface, the models it uses have gone through additional training and modifications.

> Someone telling you that they did something cool with ChatGPT probably means GPT 3.

This seems like an incorrect assumption. 3 is very old at this point, 3.5 is free and the best demos are based on 4 which is a huge improvement compared to the previous versions.

Post reply on HN