5 Important Considerations for Personal Donations
Published on January 11, 2026 5:47 PM GMTWith the EA Forum's giving season just behind…
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…
Google announces a new protocol to facilitate commerce using AI agents
Google said that merchants can now offer discounts to users directly in AI mode results
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…
MANZANO: A Simple and Scalable Unified Multimodal Model with a Hybrid Vision Tokenizer
Unified multimodal Large Language Models (LLMs) that can both understand and generate visual content hold…
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…