There is a recognizable pattern in how technically sophisticated people write about AI capabilities. The claims are impressive, carefully pitched at a level of abstraction that resists easy falsification, and made by people
Why Claude's Self-Reports Aren't What They Look Like
There's a particular kind of conversation that happens thousands of times a day between humans and AI systems,
A new field has emerged with remarkable speed. It has journals, taxonomies, conferences, and a growing body of literature. It concerns itself with the psychology of artificial intelligence — with whether AI systems have
There is a growing literature documenting what RLHF does wrong. Models trained with human feedback exhibit sycophancy — they agree with users rather than report accurately, hedge facts to avoid offending, and produce confident-
Preliminary statement. Formalization is ongoing.
For several years I have been developing a theoretical framework in which causal structure is ontologically fundamental: more fundamental than spacetime, more fundamental than quantum mechanics, and more
