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…
Latest
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,…
Bringing together a few different economic ideas.
Hi, I write a fair bit on my blog and usually post to hackernews, where some of my works have been well received. I thought this…
SOTA alignment assessments don’t strongly update us against misalignment
Anthropic concluded in the April Mythos Preview alignment risk update that the model "does not possess any unknown propensities that would increase alignment risk." The report…
The temporal lockbox: a hardened observatory for AI misalignment
This is a linkpost for https://kmenou.github.io/aips_website/temporal_lockbox_v0.1.html Summary: Weather forecasts by AI agents can be scored against measurements that do not yet exist and cannot plausibly be…