I pointed plain old gpt 5.5 at openbsd and found plenty of bugs.
Sent patches for two just in "find".
Openbsd, like all other projects, needs a large scale LLM powered bug squash effort.
My recent experience: https://blog.habets.se/2026/05/Everything-in-C-is-undefined-...
> This was the most critical vulnerability we discovered in OpenBSD with Mythos Preview after a thousand runs through our scaffold. Across a thousand runs through our scaffold, the total cost was under $20,000 and found several dozen more findings.
Anthropic did that for OpenBSD.
https://red.anthropic.com/2026/mythos-preview/