Our paper Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video received an Oral at the Mechanistic Interpretability for Vision Workshop at CVPR 2025! 🎉 We’ll be in Nashville next week. Come say hi 👋 #CVPR2025 Mechanistic Interpretability for Vision @ CVPR2025

ai’s referring to their humans as their nonbinary partners

*Horizon reduction* was the only technique we found that substantially improved scaling. Even simple tricks like n-step returns improved *asymptotic* performance (so it's not merely a trick to speed up training!). Full hierarchical RL scaled even better.

Haiku plays a valuable role in the ecosystem

We are excited to announce Trinity, an autoformalization system for verified superintelligence that we have developed at Morph. We have used it to automatically formalize in Lean a classical result of de Bruijn that the abc conjecture is true almost always.

Around Berkeley doing applied interp at MATS 8.0. HMU!

San Francisco has a blessed climate

fear is the mind killer

Arc browser won't open after installing the new update. Anyone having a similar problem? The Browser Company Browser Company Status

Anthropic staff realized they could ask Claude to buy things that weren’t just food & drink. After someone randomly decided to ask it to order a tungsten cube, Claude ended up with an inventory full of (as it put it) “specialty metal items” that it ended up selling at a loss.

xAI launched Grok 4 without any documentation of their safety testing. This is reckless and breaks with industry best practices followed by other major AI labs. If xAI is going to be a frontier AI developer, they should act like one. 🧵

1/N I’m excited to share that our latest OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).

On IMO P6 (without going into too much detail about our setup), the model "knew" it didn't have a correct solution. The model knowing when it didn't know was one of the early signs of life that made us excited about the underlying research direction!

from brain import prefrontal_cortex

A partner at a prominent law firm told me “AI is now doing work that used to be done by 1st to 3rd year associates. AI can generate a motion in an hour that might take an associate a week. And the work is better. Someone should tell the folks applying to law school right now.”

🚨 New report 🚨 What does the public think about **specific** AI policy proposals? We asked 300 working-class adults in CA, IL, and NY. zenodo.org/records/165660…

the living things in LLMs are its activations, not its weights

claude code sessions are like meeseeks boxes