281–290 of 471 posts
Earlier quoted context omitted.
you know EXACTLY what would happen in such a system.
I don't, please enlighten me.
It’s I think a normal evolution of a social norm. There will be a period of competing values.
I followed the discussion on debian-vote with interest. I'm glad that the hysterical objections lost, as they seemed quasi-religiously motivated.
> ... hysterical ... quasi-religiously ... I'm beginning to wonder if it might be the case that when my fellow citizens begin to act insane - might it be the result of foreign propaganda.
Earlier quoted context omitted.
The issue with AI is not its obvious value, it's our dependence on it. I worry what will happen to me when I am cut off for some reason. Local models are going to be really important and hopefully computing costs don't make it too prohibitive.
It's my understanding that this same debate raged when writing became a thing. Many viewed it with suspicious, or derision, as memorization was the big intellectual thing. So writing and reading back to remember was terrible. It's true it was a dependence, but the value was too high. With reading and writing a person could work on and synthesize from a far wider range of concurrent materials than one could with just…
Earlier quoted context omitted.
The issue that open source projects are facing at the moment is that it takes significantly less effort to submit a patch for review. A lot of developers who are submitting these AI patches don't necessarily understand the patch, so the onus is on the reviewer/code-owner. The reviewers are getting swamped (some reviewers are receiving 100s or patches per month). If feedback is provided at lot of the time the patch au…
The question becomes, does it take more time to create or review in the Grand scheme of the software life cycle? Because if it's still a time saver, even with the increased review load, then it's a win, correct? I'm not a coder so I have zero idea. Thoughts?
Earlier quoted context omitted.
For me, it’s not a question of whether I like it, nor where we might move in the future, but purely what is proven currently. In my experience, as in my evals, any model, including notably Fable 5 and GPT-5.6 Sol can and indeed do produce code that does not consider many edge cases, can be hard to maintain (especially Sol though it’s output has become markedly better with recent changes to Codex) and sometimes introd…
Sol and Fable are not doers, they are thinkers. Using them to "copy a few dozen HTML/JS/CSS snippets properly into a slightly obscure codebase, despite the reference being fully featured" is one of the most ineffective possible usage of those model. What you described is a job for luna. Also I suspect you overprompt, with GPT-5.6 (sol, terra and luna), a lot's of what's used to be mandatory in the AGENT.md is redonda…
I do not have an AGENTS.md in any of my repos at all, stopped using them around 5.2. I was a bit ahead of the curve with that, my evals very early showcased how limiting those tend to be, same why I never used MCP, were useless context bloat.
Will maybe make an edit explaining a bit further what the task was once I get to my computer.
Earlier quoted context omitted.
Except LLMs actually are making programmers dumber. I personally know people, people whom I know for a fact were good programmers before, who have now completely stopped using their brains. When you ask them why they did something in the code, they say "I don't know, Claude did that and I didn't really question it". There was no such analogous phenomenon with IDEs.
You can just ask Claude why it did something in the code and it will tell you Programmers just moved up a level , not dumber, we are now managers of a team of 'agent' programmers. The deliverable is now a functionality instead of a specific block of code
No, it will invent retroactively a plausible sounding reason why someone might have done it that way. These are very different things.
Earlier quoted context omitted.
His reasoning is quite fresh and interesting: > What LLMs in Debian development will do, I fear, is eliminate any incentive to scrap boilerplate or reform policies that require a lot of other senseless human effort. If I had had access to LLMs 30 years ago, I might have just had them generate the rules files, replate with complexity. So they will make Debian even more firmly what it is, and ever less likely to explor…
That's a very narrow view. If anyone could vibe code their printer drivers, maybe free software wouldn't have existed, because it would not have been needed in the first place.
If it had happened early enough, code copyright might never have even been possible and no one can deny you your machine because you can just vibe up stuff.
Earlier quoted context omitted.
This is the way it should've always been. I don't care what tool you use, but you'd better be ready to stand by and explain the results if necessary.
"This works for me, but I need help understanding why, because maybe it would help others" is a legitimate position to be in--has been since long before LLMs. I think we miss out on something when we ignore that position. I'm not saying that anybody should be obligated to review large volumes of low confidence code... just that we should not make policies that ignore shades of gray which, with some collaboration, cou…
Earlier quoted context omitted.
A good thing about the "you're the author regardless of the tool you used to produce the code" policy is that if a developer repeatedly submits poor quality AI generated code, one does not blame the model or the agent, one bans/terminates the developer.
The issue that open source projects are facing at the moment is that it takes significantly less effort to submit a patch for review. A lot of developers who are submitting these AI patches don't necessarily understand the patch, so the onus is on the reviewer/code-owner. The reviewers are getting swamped (some reviewers are receiving 100s or patches per month). If feedback is provided at lot of the time the patch au…
Or, at the very least, the community should be paying for them.