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

Gitlab’s AI-assisted code suggestions

about.gitlab.com

Post reply on HN
Print view View original

111–120 of 160 posts

Re: Gitlab’s AI-assisted code suggestions

#111

Post by colordrops »

wizzwizz4 wrote: post #24
colordrops wrote: post #11

Earlier quoted context omitted.

Unless the LLM is cutting and pasting GPL code, I don't see how this differs from an engineer learning to code by referencing open source projects then creating their own project with its own licensing. I'd imagine these models could be tuned or at least a check could be added that no licensed code is being returned.

If someone learns to program by memorising and then re-using blocks of code, they're absolutely doing it wrong – but, also, they should be able to attribute their code. Most of the techniques I used, I've invented myself (or learnt from the standard documentation). When I use a technique that I haven't invented myself, I look up where it came from. Half the time, my version is actually radically different (and my att…

> Most of the techniques I used, I've invented myself

This is a very strong statement considering most code is just rearranging existing patterns. Unless you are doing cutting edge academic research, I'm very skeptical of your claim.

Re: Gitlab’s AI-assisted code suggestions

#112

Post by SparkyMcUnicorn »

pjot wrote: post #101
simonw wrote: post #72

Earlier quoted context omitted.

I'm definitely not more junior, and I'm seeing massive productivity improvement from Copilot and GPT-4 - but I'm finding it takes a lot of expertise to get the best results, both in my ability as a programmer and in terms of knowing the best ways to use the AI tools. Learning how to get the best results of them takes a great deal of experimentation.

I’m curious what your workflow is like switching between copilot and gpt-4. I typically have an open window for each, though this can feel more cumbersome than necessary at times.

Copilot Chat is pretty great. Highly recommend signing up for the waitlist.

https://github.com/github-copilot/chat_waitlist_signup/join

Re: Gitlab’s AI-assisted code suggestions

#113

Post by wizzwizz4 »

colordrops wrote: post #111
wizzwizz4 wrote: post #24

Earlier quoted context omitted.

If someone learns to program by memorising and then re-using blocks of code, they're absolutely doing it wrong – but, also, they should be able to attribute their code. Most of the techniques I used, I've invented myself (or learnt from the standard documentation). When I use a technique that I haven't invented myself, I look up where it came from. Half the time, my version is actually radically different (and my att…

> Most of the techniques I used, I've invented myself This is a very strong statement considering most code is just rearranging existing patterns. Unless you are doing cutting edge academic research, I'm very skeptical of your claim.

You missed a bit.

> (or learnt from the standard documentation)

This means my Python code is mostly Pythonic. (The rest is kinda idiosyncratic, but I don't often get complaints.) But also:

> considering most code is just rearranging existing patterns.

I am an outspoken critic of "design patterns". They have their place, if you're working with legacy tooling like C++, Java or Rust, but if most of your work is rearranging existing patterns, you have long outgrown your tooling and you need a better programming language. (Or you're copy-paste programming and need to learn your tooling first.)

I am doing academic research, but that's besides the point. So far, I've learned that it's rather hard to be cutting-edge if you don't look at other people's work: you end up re-inventing all the wheels, and any insight you may have brought is lost in the noise.

Re: Gitlab’s AI-assisted code suggestions

#114

Post by simonw »

pjot wrote: post #101
simonw wrote: post #72

Earlier quoted context omitted.

I'm definitely not more junior, and I'm seeing massive productivity improvement from Copilot and GPT-4 - but I'm finding it takes a lot of expertise to get the best results, both in my ability as a programmer and in terms of knowing the best ways to use the AI tools. Learning how to get the best results of them takes a great deal of experimentation.

I’m curious what your workflow is like switching between copilot and gpt-4. I typically have an open window for each, though this can feel more cumbersome than necessary at times.

I actually use the ChatGPT UI more than copilot - I write code with it while I'm out walking the dog, by describing what I want, then copy and paste it into my text editor on my laptop when I get home.

I'm increasingly using my LLM CLI tool for quick lookups, and sometimes to make changes to existing code too - see https://github.com/simonw/symbex/releases/tag/1.0

Re: Gitlab’s AI-assisted code suggestions

#115

Post by leothelion_ »

SparkyMcUnicorn wrote: post #88
simonw wrote: post #69

Earlier quoted context omitted.

Did you change the way you worked to help facilitate it at all? I get great results from Copilot, but that's because I do a bunch of things to help it work for me. One example: I'll often paste in a big chunk of text - the class definition for an ORM model for example - then use Copilot to write code that uses that class, then delete the code I pasted in again later. Or I'll add a few lines of comments describing wha…

Using Copilot has taught me how to write better code comments. And the improved comment quality benefits everyone, not just the AI. Even something as simple as adding a doc block for a method can boost the quality quite a bit. I could live without it, but I'd also keep paying if the price increased.

I agree. It has made me better at articulating what I want to do, what a function does, and something as granular as what a particular loop hopes to achieve

Re: Gitlab’s AI-assisted code suggestions

#116

Post by SkyPuncher »

62951413 wrote: post #95
phil917 wrote: post #46

I just canceled my Copilot subscription last night. I definitely never saw the productivity boost that I’ve seen so many claim. I actually feel like the suggestions seemed to get worse during my month of using it for some reason. Towards the end, it started suggesting these large blocks of code (another issue I had with the interface as well) which were very not relevant to what I was attempting to write. All in all,…

Are there other people who find that IntelliJ's autocomplete suggestions and shortcuts (including live templates&Co) already do 80% of what Copilot is trying?

Yea, but that 20% is ultra powerful. It handles the fuzzy things really well and it pattern matches even better.

If I write a comment describing what I’m doing, it will generate multiple lines of correct code

Re: Gitlab’s AI-assisted code suggestions

#117

Post by __loam »

jameshart wrote: post #102
__loam wrote: post #93

Earlier quoted context omitted.

I think this view is incredibly dangerous to any kind of skills mastery. It has the potential to completely destroy the knowledge economy and eventually degrade AI due to a dearth of training data.

Okay, that’s an argument from consequences, but is the view factually wrong ?

I mean those consequences are why patent law exists. New technology may require new regulatory frameworks, like we've been doing since railroads. The idea that we could not amend law and that we need to pedantically say "well this isn't illegal now" as an excuse for doing something unethical and harmful to the economy is in my opinion very flawed.

Re: Gitlab’s AI-assisted code suggestions

#118

Post by __loam »

szundi wrote: post #96
jameshart wrote: post #81

Earlier quoted context omitted.

The trained weights of a GPT model are a frozen, static, transmissible representation. They’re not equivalent to the live state of a brain.

Pretty equivalent to the snapshot of a live brain. Those inside it are even called neurons and neural network

Machine learning neural networks have almost nothing to do with how brains work besides a tenuous mathematical relation that was conceived in the 1950s.

Re: Gitlab’s AI-assisted code suggestions

#119

Post by aerio »

pjot wrote: post #101
simonw wrote: post #72

Earlier quoted context omitted.

I'm definitely not more junior, and I'm seeing massive productivity improvement from Copilot and GPT-4 - but I'm finding it takes a lot of expertise to get the best results, both in my ability as a programmer and in terms of knowing the best ways to use the AI tools. Learning how to get the best results of them takes a great deal of experimentation.

I’m curious what your workflow is like switching between copilot and gpt-4. I typically have an open window for each, though this can feel more cumbersome than necessary at times.

>i usually have an open window for each

Do you not use the direct vscode integration? I don't think I'd use it otherwise. It's been hugely convenient with.

Re: Gitlab’s AI-assisted code suggestions

#120

Post by aerio »

SparkyMcUnicorn wrote: post #88
simonw wrote: post #69

Earlier quoted context omitted.

Did you change the way you worked to help facilitate it at all? I get great results from Copilot, but that's because I do a bunch of things to help it work for me. One example: I'll often paste in a big chunk of text - the class definition for an ORM model for example - then use Copilot to write code that uses that class, then delete the code I pasted in again later. Or I'll add a few lines of comments describing wha…

Using Copilot has taught me how to write better code comments. And the improved comment quality benefits everyone, not just the AI. Even something as simple as adding a doc block for a method can boost the quality quite a bit. I could live without it, but I'd also keep paying if the price increased.

At the current price, if it saves me a single hour in the course of a year it pays for itself. And it definitely does.
Post reply on HN