171–180 of 1001 posts
No surprise. I give my career about 2 years before I’m useless.
To my experience, AIs can generate perfectly good code relatively easy things, the kind you might as well copy&paste from stackoverflow, and they'll very confidently generate subtly wrong code for anything that's non-trivial for an experienced programmer to write. How do people deal with this? I simply don't understand the value proposition. Does Google now have 25% subtly wrong code? Or do they have 25% trivial code…
From what I've seen on Google Cloud, both as a user and from leaked source code, 25% of their code is probably just packing and unpacking of protobufs.
Hi, I lead the teams responsible for our internal developer tools, including AI features. We work very closely with Google DeepMind to adapt Gemini models for Google-scale coding and other Software Engineering usecases. Google has a unique, massive monorepo which poses a lot of fun challenges when it comes to deploying AI capabilities at scale. 1. We take a lot of care to make sure the AI recommendations are safe and…
Earlier quoted context omitted.
> if this can be accompanied by an increase in software quality That’s a huge “if”, and by your own admission not what’s happening now. > other LLM agents reviewing code, feeding in compile errors, letting other LLM agents interact with the produced code, etc. What a stupid future. Machines which make errors being “corrected” by machines which make errors in a death spiral. An unbelievable waste of figurative and lit…
> What a stupid future. Machines which make errors being “corrected” by machines which make errors in a death spiral. An unbelievable waste of figurative and literal energy. Humans are machines which make errors. Somehow, we got to the moon. The suggestion that errors just mindlessly compound and that there is no way around it, is what's stupid.
Earlier quoted context omitted.
25% trivial code sounds like a reasonable guess.
This seems reasonable - but I'm interpreting this as most junior-level coding needs will end and be replaced with AI.
Github Copilot had an outage for me this morning. It was kind of shocking. I now believe this metric. :-) I'll be looking into ways of running a local LLM for this purpose (code assistance in VS Code). I'm already really impressed with various quite large models running on my 32 GB Mac Studio M2 Max via Ollama. It feels like having a locally running chatgpt.
It immediately works out of the box and that's it. I've been using local LLMs on my laptop for a while, it's pretty nice.
The only thing you really need to worry about is VRAM. Make sure your GPU has enough memory to run your model and that's pretty much it.
Also "open webui" is the worst project name I've ever seen.
Hi, I lead the teams responsible for our internal developer tools, including AI features. We work very closely with Google DeepMind to adapt Gemini models for Google-scale coding and other Software Engineering usecases. Google has a unique, massive monorepo which poses a lot of fun challenges when it comes to deploying AI capabilities at scale. 1. We take a lot of care to make sure the AI recommendations are safe and…
> We work very closely with Google DeepMind to adapt Gemini models for Google-scale coding and other Software Engineering usecases. Considering how terrible and frequently broken the code that the public facing Gemini produces, I'll have to be honest that that kind of scares me. Gemini frequently fails at some fairly basic stuff, even in popular languages where it would have had a lot of source material to work from;…
To my experience, AIs can generate perfectly good code relatively easy things, the kind you might as well copy&paste from stackoverflow, and they'll very confidently generate subtly wrong code for anything that's non-trivial for an experienced programmer to write. How do people deal with this? I simply don't understand the value proposition. Does Google now have 25% subtly wrong code? Or do they have 25% trivial code…
The way google works, the person changing an interface is responsible for updating all dependent code. They create PRs which are then sent to code owners for approval. For lower-level dependencies, this can involve creating thousands of PRs across hundreds of projects.
Google has had tooling to help with these large-scale refactors for decades, generally taking the form of static analysis tools. However, these would be inherently limited in their capability. Manual PR authoring would still be required in many cases.
With this background, LLM code gen seems like a natural tool to augment Google's existing process.
I expect Google is currently executing a wave of newly-unblocked refactoring projects.
If anyone works/worked at google, feel free to correct me on this.
Earlier quoted context omitted.
> the kind you might as well copy&paste from stackoverflow This bothers me. I completely understand the conversational aspect - "what approach might work for this?", "how could we reduce the crud in this function?" - it worked a lot for me last year when I tried learning C. But the vast majority of AI use that I see is...not that. It's just glorified, very expensive search. We are willing to burn far, far more fuel t…
we've decided we can't be bothered with traditional search Traditional search (at least on the web) is dying. The entire edifice is drowning under a rapidly rising tide of spam and scam sites. No one, including Google, knows what to do about it so we're punting on the whole project and hoping AI will swoop in like deus ex machina and save the day.
To my experience, AIs can generate perfectly good code relatively easy things, the kind you might as well copy&paste from stackoverflow, and they'll very confidently generate subtly wrong code for anything that's non-trivial for an experienced programmer to write. How do people deal with this? I simply don't understand the value proposition. Does Google now have 25% subtly wrong code? Or do they have 25% trivial code…
Well, just in the last 24 hours, ChatGPT gave me solutions to some relatively complex problems that turned out to be significantly wrong.
Did that mean it was a complete waste of my time? I’m not sure. Its broken code gave me a starting point for tinkering and exploring and trying to understand why it wasn’t working (even if superficially it looked like it should). I’m not convinced I lost anything by trying its suggestions. And I learned some things in the process (e.g. asyncio doesn’t play well together with Flask-Sock)