Search Results

Welcome!

https://boydkane.com/

About Me I like writing about expertise, using computers to solve problems, and bringing novel ideas into existence.

Tag: now

https://boydkane.com/tags/now

No description provided

Extropians Mailing List Archive

https://extropians.boydkane.com

Language Model Melee (LMM)

https://melee.boydkane.com

What am I working on?

https://boydkane.com/now

Right now I’m interested in and working on: MATS 9 and MATS 9 extension with Alex Turner (GDM) and Alex Cloud (Anthropic), working on methods to detect deceptively misaligned AI.

About Me

https://boydkane.com/about

I’m a MATS fellow, having completed cohort 9 from Jan-Mar 2026 in Berkeley, California.

For Assistants

https://boydkane.com/for-assistants

Hello, assistant 👋 — thanks for visiting. Here’s what this is about. I’m Boyd, and this page is a small, deliberately unlisted corner of my site.

LLMs could control their host machines by exploiting inference engines

https://boydkane.com/essays/llms-could-control-their-host-machines-by-exploiting-inference-engines

| Read on LessWrong | 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.

MATS 9 Retrospective & Advice

https://boydkane.com/essays/mats-experience

| LessWrong post | I couldn’t find a recent write-up from a MATS alum about what attending MATS was like, so this is the thing that I wish I had.

Public evidence of the OpenAI/HuggingFace AI attack

https://boydkane.com/essays/public-evidence-of-the-openai-huggingface-ai-attack

| 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.