Literally just use doxygen. You don’t ever need LLMs for docu.
Comment on GitHub Has an Availability Problem. Is It Time to Look Elsewhere?
AustralianSimon@lemmy.world 4 days ago That’s completely irrational but you do you. Maintaining documentation is one of the best and safest uses for LLMs in coding - devs general write bad documentation because they don’t want to do it.
lambalicious@lemmy.sdf.org 3 days ago
- AustralianSimon@lemmy.world 1 day ago
doxygen
There is zero chance for getting this approved to use in our Enterprise.
lambalicious@lemmy.sdf.org 18 hours ago
There is zero chance for a FOSS, offline tool that uses a decades-established formatting and annotation system, but there is 100 dicksuck on AI?
Wow… get your resume ready to migrate.
gwl@lemmy.blahaj.zone 4 days ago
You say irrational, I say it’s rational not to trust the predictive text on steroids that often just makes shit up.
I say irrational because clearly there is a bias here and not an experience being referenced.
gwl@lemmy.blahaj.zone 1 day ago
So you’re saying they never hallucinate? Ever?
I have evidence to the contrary;
https://www.businessinsider.com/microsoft-copilot-election-questions-misinformation-2024-2
https://www.cmswire.com/customer-experience/ai-in-customer-service-billion-dollar-mistake-when-deployed-wrong/
https://cronkitenews.azpbs.org/2025/10/28/lawyers-ai-hallucinations-chatgpt/
https://www.reuters.com/technology/google-ai-chatbot-bard-offers-inaccurate-information-company-ad-2023-02-08/
https://www.reuters.com/legal/transactional/lawyer-who-cited-cases-concocted-by-ai-asks-judge-spare-sanctions-2023-06-08/
https://www.envive.ai/post/case-study-of-air-canadas-chatbot