Boyd

I use the various language models a lot for my research, and this means I end up seeing quite a lot of their failure modes.

Read on LessWrong Comment on HN Large language models often take actions running on one computer (via an agentic harness such as Claude Code or Codex), however the LLMs' responses to prompts are computed on a different computer with GPU access.

Read on LessWrong The problem This tweet recently highlighted two MATS mentors talking about the absurdly high qualifications of incoming applications to the AI Safety Fellowship: Another was from a recently-announced Anthropic fellow, one of 32 fellows s

Read on LessWrong Claude & I vibecoded an interface for the extropians mailing list. It's live! Have a look here: extropians.boydkane.com/.

Read on LessWrong American bald eagle caws angrily in the distance Whoa whoa whoa, just hear me out.

Read on LessWrong I'm a MATS 9 extension fellow, and usually my week is spent trying to find better ways of evaluating Large Language Models.

Read on LessWrong Basically every meeting is scheduled with an explicit duration.

Read on LessWrong Around July last year I decided I was going to go all in on technical AI safety research.

Hey! I semi-frequently link to essays that are still being written, and track when these links get clicked.

Often, I'll find myself wanting to reference AI safety papers or findings, knowing vaguely that something's been shown to be true, but not being able to find the source paper.