(I am confused about) Non-linear utilitarian scaling
I had some vague thoughts about scaling in utilitarian-ish ethics, noticed I was confused about…
Category: Opinion
Hello, World of Mechanistic Interpetability
This post is an introduction for the series of posts, which will be dedicated to…
Schedule meetings using the Pareto principle
Basically every meeting is scheduled with an explicit duration. This is convenient for scheduling, but…
What Are We Actually Evaluating When We Say a Belief “Tracks Truth”?
I’ve been thinking about this issue a while. Certainly since grad school. The classic definition…
Was Anthropic that strategically incompetent?
This is pretty vague. It might be vague because Dario doesn't have a plan there,…
We Started Lens Academy: Scalable Education on Superintelligence Risk
The number of people who deeply understand superintelligence risk is far too small. There's a…
Emergent stigmergic coordination in AI agents?
Post written up quickly in my spare time. TLDR: Anthropic have a new blogpost of…
Some models don’t identify with their official name
When you ask an LLM "who are you?", some models don't answer with their official…
My Willing Complicity In “Human Rights Abuse”
Note on AI usage: As is my norm, I use LLMs for proof reading, editing,…
How post-training shapes legal representations: probing SCOTUS opinions across model families
Papers like Turner et al 2025 and Betley et al 2026 have underscored the consequences of training…