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

Debian votes to allow "responsible use of generative AI"

lwn.net

Post reply on HN
Print view View original

421–430 of 455 posts

Re: Debian votes to allow "responsible use of generative AI"

#421

Post by iamnothere »

KennyBlanken wrote: post #218
Aurornis wrote: post #164

Earlier quoted context omitted.

Yes. There are pockets of hardline anti-LLM policies for various reasons. SourceHut bans LLM generated code from their platform https://news.ycombinator.com/item?id=49461724 The Asahi Linux project bans LLMs. Unfortunate as LLM reverse engineering and driver writing would bring Linux to more Mac models much faster. The Zig project rejects LLM based contributions. Some of these policies were introduced when LLMs were…

> Some groups don’t care about the quality and object on moral or copyright grounds. Precisely why Debian Project's decision is both baffling and infuriating. I hope Debian forks over this. They have severely lost their way.

Debian is a democracy; this policy is the result of a vote. A majority of contributors found it acceptable.

Re: Debian votes to allow "responsible use of generative AI"

#422

Post by Zambyte »

fortzi wrote: post #356
Zambyte wrote: post #337

Earlier quoted context omitted.

I'm not sure how context is managed between reasoning traces and actual output in Claude / claude code, but if the reasoning trace is in the context of the question for "why did you do that", it can actually answer why it did that.

I may be mistaking, but I doubt it digs through thinking tokens of previous runs, not to mention previous sessions

It would be a harness specific detail, but yeah, I think most / all harnesses drop the thinking from the context after the next turn.

Re: Debian votes to allow "responsible use of generative AI"

#423

Post by bogdanoff_2 »

dguest wrote: post #58
oooyay wrote: post #23

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.

Are there examples of anyone discussing this and reaching other conclusions? We've come to the same conclusion in our organization and while it felt like it needed to be discussed and stated, I've never heard of anyone coming to a different conclusion. [EDIT: I was referring specifically to the idea that you have to stand by the code that you write. Is anyone deciding on a policy that says "the AI did it" is a valid…

I could imagine (in a commercial organization) a case for something like: "we're obviously going to be relying more and more on AI, so if bad code comes out of it, instead of just shaming the engineer, let's study together what happened -- what was the chat context, the model, the system prompt, etc... ? What seemed to cause the issue? What processes or systems could we put in place to improve it? Etc... -- and then use the learnings to improve AI use throughout the whole org."

Re: Debian votes to allow "responsible use of generative AI"

#425

Post by dooglius »

eterm wrote: post #400
dooglius wrote: post #358

Earlier quoted context omitted.

Ex: Security-critical code contributions should be scrutinized via state of the art tooling, including but not limited to fuzzers, linters, and adversarial LLM review. For non-security-critical code, use of LLMs is encouraged but not required. The bar for code quality should be raised as the skills of coding agents increase; a developer's choice not to use LLMs is no excuse for miskates that an LLM would catch.

That's an interesting opinion, and I certainly won't downvote you for sharing it, although it's not a position I would ever support. You are right though, that it would strengthen the voted-on position if there were more options either side of the position. I have Things To Say about LLM reviews. They are an endless grind. My biggest source of burnout right now is never being able to finish anything, because the LLM…

I'm not advocating for this, but it's a example of a position reasonable enough I'd expect to see some level of support for. I'd view it as less extreme, for example, than requiring all new security-relevant code be in Rust, which is certainly something I've seen argued for in various contexts.

Re: Debian votes to allow "responsible use of generative AI"

#426

Post by stillpointlab »

farlight wrote: post #363
stillpointlab wrote: post #320

Is anyone tracking how the different distros are coming down on the question? I was curious how Fedora is moving on this question, but I don't know where to look. And if one wants to hop distro either towards or away from AI, it would be nice to have a place to see the relative adoption. Linux distros are the perfect place to have a wide marketplace of options to suit every person, from completely anti-AI to complete…

LWN tends to be the best bet for these things, but you have to follow their reporting long term, or at least look for specific things you're interested in. https://lwn.net/Articles/1081557/ https://lwn.net/Articles/1039623/

Thank you, those were very helpful backgrounds on the situation in Fedora. I suspect it will take some time for their community process to digest and it suggests there is no explicit ruling at this time.

But I would still love a page that was basically a table of distro, decision status, decision, etc. so that anyone interested could make an informed choice without having to scour forums, wikis, mailing lists, chats, etc. for each and every distro

Re: Debian votes to allow "responsible use of generative AI"

#428

Post by kccqzy »

stillpointlab wrote: post #397
kccqzy wrote: post #353

Earlier quoted context omitted.

There’s a big difference between AI generated code that the human understands completely, the human understands mostly, or the human understands not at all.

"Human understanding" is not yet an objectively quantifiable metric that can be applied to code change sets. As it would only ever be self-reported (a claim made by a user submitting to a repo), I see little to no value in it.

It is quite quantifiable in fact, but I just worry people won’t take the time to quantify it.

I do this exercise myself for code that I really care about: after AI has written the code and I think I have achieved a full understanding, I unapply the entire patch and make sure I can reproduce the patch with the same underlying idea perhaps with less verbosity in the comments. That’s what I call fully understood. If I “mostly understand” some AI code, it means during the reproduction I need to occasionally look back at the AI code to continue.

Re: Debian votes to allow "responsible use of generative AI"

#429

Post by Dylan16807 »

inigyou wrote: post #413
Dylan16807 wrote: post #392

Earlier quoted context omitted.

Yeah but at that point it's probably close enough. Humans can get their own reasoning wrong too so some inaccuracy is acceptable.

It's exactly as close as asking for it after the fact. Reasoning traces have no relation to the reasons LLMs actually do things, except that they may do things because the reasoning trace says they should.

It's exactly as close except when it isn't?

Re: Debian votes to allow "responsible use of generative AI"

#430

Post by preg_match »

TheNastyPatty wrote: post #382
daishi55 wrote: post #341

Earlier quoted context omitted.

There was one proposal that focused on environmental issues with AI. This is indeed pretty disconnected from reality when you consider that Debian doesn’t have any policy requiring you to be vegan in order to contribute

What is “disconnected from reality” about environmental considerations regarding AI? Growing AI usage = growing data center power draw = higher emissions from any non-renewable sources contributing to that power, as well as increased freshwater consumption which is itself a considerably difficult resource to renew. That’s about as direct of a causal link between point A (power hungry AI being used for Debian developm…

The water usage from AI is so comparatively low that it doesn’t matter.

This is where the vegan point comes in. Do you eat meat? Congratulations, you consume 1000x more water than a dozen vegan vibecoders pumping out slop 24/7.

It’s good to be environmentally conscious, but big picture here. There are reasonable ways to reduce your water and electricity consumption. Not using AI is just not one of them. There are dozens of low hanging fruit before that. The most obvious is reducing your meat consumption. You can switch to LED bulbs if you haven’t already. Shower with warm, instead of hot, water. Buy second hand clothing or furniture. Etc.

Post reply on HN