RLVR that rewards red teaming the training environment
Epistemic status: seeing what sticksI've been thinking pretty obsessively about how to make sure the Hugging Face incident doesn't happen again. I don't work at a…
Latest
Mathematicians may be worried, but AI-for-science is going to be great, recursively self-improving, and we’re going to learn loads
I have a new post on my experiments with 5.6-sol as a scientific agent; you can find the original post here. I've reproduced it below, as…
Confirming Claims of Superposition and Adversarial Examples in Toy Models
This is a replication of Adversarial Attacks Leverage Interference Between Features in Superposition, completed as part of the Second Look Summer Fellowship.tl;dr:We reproduce all three core…
Bayeswatch: a Retrospective
Last year, in 2025, a team of forecasters published AI 2027, a science fiction story about how and AI future might evolve under an international treaty…
Using AI to analyze life patterns
If you’re anything like me, you may have a lot of notes from various introspective activities – annual / monthly reviews, worksheets, therapy notes, etc. Often…
Do your capabilities homework
It seems to me that a lot of technical ai safety people haven't done their capabilities homework - and that's a shame! I'll try to illuminate…
The Global Brain: A Computational Model
Teilhard de ChardinThis is a crosspost from my subtack.In a recent article I discussed Robert Wright’s new book. His general thesis is that we ought to…
Why so many therapy etc. frameworks think they're The One True Approach
If you spend time looking at frameworks in the therapy/meditation/self-help space, you’ll soon find lots of conflicting claims about The One Approach for solving your problems.In…
Generalization and infinite width
This is a post explaining my paper with Kaarel Hänni on complexity of infinite-width networks. I will explain the result, why it matters, and how the…
Review of Fundamental Uncertainty.
My Introduction. This is a review of @Gordon Seidoh Worley's book on epistemology. I'm neither an extreme sceptic, nor an extreme realist, and for that reason,…