2026-09-09 01:02 UTC
@nullagent@partyon.xyz I don't think that's at all a serious position.
Yes in their position you probably want someone running whatever heuristic vuln scanning utilities attackers are using, even if some of those are LLM-slop.
You do NOT need to be actually using "LLM code review" from those things as part of your development process. You can take a list of potential issues, condensed down to 1 line descriptions with a pointer to the line/function in your code, and actually review them like you would anything out of a static analysis tool.
Replies (1)
-
@nullagent@partyon.xyz 2026-09-09 01:19
To be clear... I do NOT see formal LLM code review of general PRs on the github repo in question. There really seems to be NO formal LLM process or policy here. ALL I see clear evidence of is that ONE dev pushed an AGENTS.md to their branch. I do not see the systemic LLM structure you mention above. I'm not a contributor so i don't know their processes other than whats on their github. @dalias@hachyderm.io