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

141–150 of 160 posts

Re: Gitlab’s AI-assisted code suggestions

#141

Post by visarga »

__loam wrote: post #118
szundi wrote: post #96

Earlier quoted context omitted.

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.

You can say that if you want to nitpick, but there are recent studies showing that neural and brain representations align rather well, to the point that we can predict what someone is seeing from brain waves, or generate the image with stable diffusion.

https://sites.google.com/view/stablediffusion-with-brain/

I think brain to neural net alignment is justified by the fact that both are the result of the same language evolutionary process. We're not all that different from AIs, we just have better tools and environments, and evolutionary adaptation for some tasks.

Language is an evolutionary system, ideas are self replicators, they evolve parallel to humans. We depend on the accumulation of ideas, starting from scratch would be hard even for humans. A human alone with no language resources of any kind would be worse than a primitive.

The real source of intelligence is the language data from which both humans and AIs learn, model architecture is not very important. Two different people, with different neural wiring in the brain, or two different models, like GPT and T5 can learn the same task given the training set. What matters is the training data. It should be credited with the skills we and AIs obtain. Most of us live our whole lives at this level and never come up with an original idea, we're applying language to tasks like GPT.

Re: Gitlab’s AI-assisted code suggestions

#142

Post by tomashubelbauer »

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,…

I also find Copilot to be rather underwhelming and half the time I find myself wishing it didn't go as overboard with the suggestions as it does. Sometimes it suggests exactly what I want to type and then adds a bunch of extra crap towards the end so it is the same amount of effort to type it manually or accept the suggestion and erase what I don't need.

Also its inability to match parens and braces/brackets is legendary. So annoying.

But! It is extremely helpful for filling in error messages. I don't think I wrote a `throw new ` line fully since I started using it. The quality and information density of my error messages has increased considerably.

Not sure if it is worth keeping for just that but it is a nice benefit.

Re: Gitlab’s AI-assisted code suggestions

#143

Post by DrakeDeaton »

lostmsu wrote: post #85
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,…

Just today Copilot saved me close to 1 hour of typing and replaced it essentially with ~1 minute of pressing Tab. I was hooking IAudioClient COM class to capture and silence arbitrary app's audio, and as soon as I wrote signatures for its members Copilot was able to generate skeletal stub implementation with logging as well as hooking code totaling about 150 lines of Rust.

This is an example of why codebases with strict typing & clear conventions will benefit the most from copilot.

Re: Gitlab’s AI-assisted code suggestions

#144

Post by wouldbecouldbe »

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,…

Yeah not worth it at the moment. Often it annoys me be overwriting legitimate suggestions from the editor.

Only reason I still have it is because the beta claims to have GPT-4 integration and that could prove to be a very powerful feature. But I still haven;t gotten an invite to install.

Re: Gitlab’s AI-assisted code suggestions

#146

Post by az226 »

johndough wrote: post #39
nonameiguess wrote: post #17

Earlier quoted context omitted.

I guess we'll see what the legal system says, but it's nearly impossible for me to imagine how anyone could ever justify saying a system trained on potentially millions of separate open-source projects can then be said to universally produce derivative works of any specific project it trained on. On the other hand, if a developer using this tool then goes and tells it "please write me a C library in the style of GNU…

GitHub Copilot copying Quake's fast inverse square root function is a famous example where Copilot copied GPL-licensed code only given the comment // fast inverse square root https://news.ycombinator.com/item?id=27710287

Unironically — it happens that Carmack said he got it from someone else.

Re: Gitlab’s AI-assisted code suggestions

#148

Post by 0xjnml »

Chiron1991 wrote: post #18
ases wrote: post #4

All the code examples on this page are doubling any brackets ([], {}, ()). How have they managed that? Not a fantastic first impression of its capabilities...

Not only that, but the Golang example is full of errors. Parameter definitions don't have colons between name and type. The map for seen elements is declared as a, but later referenced to as m. The append instruction references uniques, which is undefined. The return statement also references uniques.

The Go code shown now is both syntactically valid and semantically correct: https://go.dev/play/p/GDki9v78jMM

I can't check how it looked 15 hours ago.

Makes me wonder if it was manually corrected and is thus a fake example now.

Re: Gitlab’s AI-assisted code suggestions

#149

Post by dnsmichi »

tallytarik wrote: post #131

GitLab was rather quick to board the AI hype train this year. Fine - they don't want to look like they're behind the curve, have to please investors, and whatever else. But IMO there are plenty of other places to add real value across the GitLab product with AI/ML features. Here, it just looks like they saw GitHub do something and felt a need to copy it. But two years late, and worse. As a longtime GitLab user (and o…

GitLab team member here. Thanks for your feedback.

> But IMO there are plenty of other places to add real value across the GitLab product with AI/ML features.

True, and after starting with ML experiments, the product and engineering teams have been working on new features for entire DevOps lifecycle. All AI workflows on the DevSecOps platforms are described in the GitLab Duo announcement blog post https://about.gitlab.com/blog/2023/06/22/meet-gitlab-duo-the... and website https://about.gitlab.com/gitlab-duo/

I'll share a few highlights that I am personally excited about

- Explain and help fix security vulnerabilities. From my personal experience, I often find CVEs hard to read, especially when I am not the author of the code to fix. Getting help from AI can reduce entry barriers and make development for efficient. Security is everyone's responsibility these days. This follows the AI assisted feature to explain code in general. "What does this magic loop with memcpy do?" might not stay magic anymore, easing the path to code refactoring, improving performance, and reduce the resource usage footprint.

- Summarize issue comments. Feature proposals or bug analysis can have long comment threads that require reading time. AI will help get the gist and better contribute to what has been discussed.

- Summarize MR changes, to avoid reading long change diffs. This helps with faster (code) review cycles. I tested it this week with an MR for our handbook in https://gitlab.com/gitlab-com/www-gitlab-com/-/merge_request...

I'd also like to see AI helping fix CI/CD pipelines fast. Proposal in https://gitlab.com/gitlab-org/gitlab/-/issues/386863 I shared some thoughts in a new talk "Observability for Efficient DevSecOps Pipelines", slides in https://go.gitlab.com/VDAvMw (GitLab blog post coming soon, https://gitlab.com/gitlab-com/www-gitlab-com/-/issues/34296)

Additionally, I learned some new ideas at Cloudland last week, regarding product owner requirements list verification, and end-to-end test automation with AI. Need to create feature proposals :-)

> As a longtime GitLab user (and onetime contributor!),

Thanks for contributing. I'd like to invite you to share your ideas about AI features across the platform :)

When you look at the DevOps lifecycle (image in https://about.gitlab.com/gitlab-duo/) from plan/manage to create, verify, secure, package, release, deploy, monitor, govern - where do you see yourself, and where do you spend the most time in?

Second question: Which process feels the most inefficient? After identifying answers to the questions, please check the AI features https://docs.gitlab.com/ee/user/ai_features.html and/or open new feature proposals for GitLab https://gitlab.com/gitlab-org/gitlab/-/issues/new?issuable_t... You can tag @dnsmichi so I can engage with your ideas. Thanks!

Re: Gitlab’s AI-assisted code suggestions

#150

Post by darkerside »

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,…

I found the same, and I was really hoping for a productivity boost. I really wonder how much this correlates to developer speed. I code using Vim and type probably 80-100wpm. Typing is usually not the bottleneck for me. Thinking is. Copilot is good at typing, but not good at thinking. IME. Occasionally it will surprise me with a valid contribution, which I then need to check just as carefully as if I were writing it myself.
Post reply on HN