Evan ProdromouYes
Yes, but...
No, but...
No
Poll ended at .
Hey, all. Thanks so much. I'm yes, but. I find that using AI to scan code and documents can be really helpful in finding high-level errors. But it's not perfect, and has false negatives and false positives. I think it's a good tool for people who understand the problem space, but might not be great for someone who isn't familiar with what the code does or the docs mean.
Adële 🐁!@evan I agree with you. These tools can be useful if you know what you do...
https://adele.pages.casa/md/blog/sometimes-i-use-llms.md
https://adele.pages.casa/md/blog/sometimes-i-use-llms.md
prom™️
Jason Parker (he/they)@evan I'm not a big fan of AI in general (the possibilities it opens are scary, and we're already seeing where that's going), but I think analyzing documents -- if, and only if, it isn't your only check -- is one of very few use-cases where it's more helpful than damaging.
Bodling
Moreno Colaiacovo 🌍@evan I voted yes because an additional check is always useful, whether it's by an AI or a human. LLMs can make mistakes and overloook errors, but so do humans.
Faraiwe
Christian Yoga 
John Abbe (aka Slow)@evan Done w this question. Fully set it down when I realized AI is 'just' the latest religious war among coders. (Perhaps second only to tabs-vs-spaces.)
Now I'm consciously trying to participate in AI conversations (if I participate at all) in ways that break the "Is AI good or bad?" framing, rather than reifying the fight.
Firefox did this in code: big button to turn AI off, little buttons to turn on LLM-powered features, starting w on-device translation which ~everyone understands & wants.
Philip Mallegol-Hansen@evan The definitions of “OK” and “AI” are pretty darn load bearing in this question.
I’m “No, but”… it hinges on my exact assumption that AI means large private LLMs, and OK means “an ethical thing to do”.
(Not a complaint, I know you can’t exhaustively define every word in existence)
Alex Chapman@evan Yes but don't just rely on what the AI says, actually make sure its correct.
James M.
MattChippytea@evan no, because ai is a societal and environmental disaster, but this is not the worst use it could be put to
Frank Heijkamp@evan
By #ai you probably mean #llm?
Personally I'm not very fond of them, some people however don't seem to be able to function without them anymore.
The definition of what an error is can be very wide or very narrow. To assess 'correctness' can entail several things.
Was the correct syntax, spelling or grammar used? Does the logic contain any obvious mistakes? The topic of ethics is very tricky as an LLM is unable to do any actual reasoning. The output can look convincing, but is it really?
Gaëtan Perrault@gatesvp
The definition of #ai is too broad.
Technology sold as artificial intelligence is unable to reason and it's therefore very much up to discussion if one can call it intelligent.
A #llm or Large Language Model in full is a parroting machine that is able to generate a text that looks convincing. Looking convincing doesn't necessarily mean it is correct. Please also keep in mind all #llm's have implicit bias and explicit filters that heavily skew the output. This makes their use limited.
Ryan Lounsbury@evan I feel like this is one thing AI is week suited to do.
maarten brouwers@evan I went with no but, as there is hardly any ethically trained ai. But if your employer forces you, you are not a bad person when you comply. Also using it for review is the less evil use of ai, where it might help improve / inspire quality, and not adds up to the slop, although I fear it might make your critical muscle lazy.
Olivia Vespera@evan We know large language models can't exist in their current form without using copyrighted data.
How are you ensuring your model doesn't contain copy righted data?
andif you're going to use a model by one of the big tech providers, there's going to be the issue of complicity with what they're doing.
@evan As a software engineer, I've kind of being doing this for years. The newer GenAI tools are more powerful than the older ones I had many years ago, but that's better not new.
bignoseAn #LLM, as provided today, no. They are all trained on data for which they do not respect copyright; they all use gargantuan scarce resources in training and inference; they are proprietary and centralised and any dependency on them is begging to be exploited. It's never okay to take part in that.
But AI existed long before LLMs, and will continue long after the LLM bubble pops. It's fine to use an AI (e.g. spell check) that doesn't have those problems, to analyse documents for errors.
S.Tori
Dave M7TLB 🐞 post #oggcamp2026@evan Yes, but... you must check the corrections yourself.
Mohauk · mohauk.net@evan Whenever you are familiar with the topic you intend to analyze, but not if you are using AI as a tutor.
Nadia/Надя/नाडिया/娜迪亚/ نادية@evan It may help with exploring the space of potential proofs of correctness for formal verification tools. Ultimately, something needs to check that it's doing the right thing somehow.
Jef Poskanzer@evan As a freeware publisher I get bug reports and it's utterly obvious which ones are AI nonsense.
Jessamyn@evan @jef we see a lot of people in the Wikipedia universe who are clearly writing their various statements for or against deletion nominations, categorization discussions, and other administrative stuff and it's also really clear what's been written by AI because it's so wordy while saying not much .
McNeely@evan I have a very hard time imagining that "AI" (which is not a specific thing but that's a whole other poll/discussion) can do a better job than actual purpose built tools for static analysis
@McNeely have you tried it?
@evan "it" is a little vague here. I've used AI code review tools which are better than nothing when I was the sole developer on a project at a startup. I've used tools like SonarQube and linters for static analysis. I think that in the end it works but I'm not sure it's worth the cost/trade-offs.
Manu