5 Important Considerations for Personal Donations
Published on January 11, 2026 5:47 PM GMTWith the EA Forum's giving season just behind…
Category: Opinion
Stretch Hatchback
Published on January 11, 2026 4:40 PM GMT Our family has half a Honda Fit,…
We need a better way to evaluate emergent misalignment
Published on January 11, 2026 4:21 PM GMTTLDRQwen3-4B fine tuned on several real life, benign…
Should the AI Safety Community Prioritize Safety Cases?
Published on January 11, 2026 11:56 AM GMTI recently wrote an Introduction to AI Safety…
Coding Agents As An Interface To The Codebase
Published on January 11, 2026 10:31 AM GMTAttack DogsI mentioned previously that coding agents kind…
Why AIs aren’t power-seeking yet
Published on January 11, 2026 7:07 AM GMTRecently, I spent a couple of hours talking…
Theoretical predictions on the sample efficiency of training policies and activation monitors
Published on January 10, 2026 11:50 PM GMTI'm worried about AI models intentionally doing bad…
If AI alignment is only as hard as building the steam engine, then we likely still die
Published on January 10, 2026 11:10 PM GMTCross-posted from my website. You may have seen…
Possible Principles of Superagency
Published on January 10, 2026 9:00 PM GMTPrior to the era of superintelligent actors, we’re…
The Case Against Continuous Chain-of-Thought (Neuralese)
Published on January 10, 2026 8:32 PM GMTMain thesis: Discrete token vocabularies don't lose information…