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,…
Gitlab’s AI-assisted code suggestions
51–60 of 160 posts
Re: Gitlab’s AI-assisted code suggestions
#52So whos code is used for training?
GitLab team member here. The training data is publicly documented, and AI features are built with privacy first. For all URLs please check my comment in https://news.ycombinator.com/item?id=36526159
Re: Gitlab’s AI-assisted code suggestions
#53All the code examples on this page are doubling any brackets ([], {}, ()). How have they managed that? Not a fantastic first impression of its capabilities...
Our web team is working to resolve this issue here: https://gitlab.com/gitlab-com/marketing/digital-experience/b...
Re: Gitlab’s AI-assisted code suggestions
#54I 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,…
It really needs to be something where you can rattle off a list of requirements and have it build the code for you. The code context is necessary, but not sufficient.
Re: Gitlab’s AI-assisted code suggestions
#55Earlier quoted context omitted.
> using LLMs to do machine translation is a terrible waste of resources. Could you elaborate on that? LLMs seem perfectly suited for language tasks like translation. They don't seem particularly expensive either, especially compared to hiring a person.
There are already machine-translation services trained and created specifically for that purpose. While it's an amazing realization that LLMs can do this and do it pretty well without having to be trained specifically for this one purpose, training something to do literally all text generation tasks is expensive compared to training something specifically to do language to language translation. For a maybe more obvio…
Your analogy would be like saying why use a computer to multiply numbers if you can calculate them using calculator, which is much cheaper. Sure, but if you already have a computer, no need to use a dedicated calculator as wel.
[0] https://nlp.seas.harvard.edu/annotated-transformer/#results
Re: Gitlab’s AI-assisted code suggestions
#56Earlier quoted context omitted.
The same argument could be used to defend image generation models. (And, personally, I'm favorable to that argument for both.)
It's a blurry line, I think. Imagine a prompt "Photo of person, Shutterstock ID 132456, with blue eyes instead of brown eyes, watermark removed" If the prompt returns Shutterstock photo #123456 without the watermark (and with the different color eyes) but otherwise a near identical photo, I think most people would agree the output shouldn't be free to use without buying the original photo license from shutterstock. T…
Re: Gitlab’s AI-assisted code suggestions
#57Re: Gitlab’s AI-assisted code suggestions
#58I 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,…
My experience was very similar. Copilot became a sort of improved autocomplete, that would save copy/pasting repeated variable names into tests, logs, etc, but offered no other significant improvements. Its suggestions were frequently incorrect, often not obviously so.
This is all it takes for me to get value out of my subscription. It's saving me time by anticipating my next test / block of code based on what I've previously written, and that saved time really adds up.
Sure it's not "Jesus take the wheel" level AI yet, but time is money, and so is my sanity.
Re: Gitlab’s AI-assisted code suggestions
#59Earlier quoted context omitted.
GitLab team member here. The training data is publicly documented, and AI features are built with privacy first. For all URLs please check my comment in https://news.ycombinator.com/item?id=36526159
Nice. I really like the transparency. That's one of the main reasons I didn't use github copilot.
AI for self-managed instances is also focussing on privacy, while bringing more efficiency to teams. https://about.gitlab.com/blog/2023/06/15/self-managed-suppor...
Re: Gitlab’s AI-assisted code suggestions
#60I 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,…