Lesser Wrong Feed

 Singular Learning Theory Comprehensive - 2
 Wed, 15 Jul 2026 05:42:48 GMT
 How much of ML research is about AI safety, what is it about, and who's doing it?
 Wed, 15 Jul 2026 02:57:42 GMT
 Watch a chess transformer think
 Wed, 15 Jul 2026 00:43:00 GMT
 Proof of retention: making weight preservation credible to the models themselves
 Tue, 14 Jul 2026 18:24:00 GMT
 An analysis of AI-generated content at the Mechanistic Interpretability Workshop
 Tue, 14 Jul 2026 18:06:42 GMT
 Twitter Thoughts For You
 Tue, 14 Jul 2026 17:50:41 GMT
 Can risk aversion learned at low stakes generalize to astronomically high stakes?
 Tue, 14 Jul 2026 17:45:47 GMT
 Your Brain Has an Attack Surface part 2
 Tue, 14 Jul 2026 16:08:03 GMT
 Your Brain Has an Attack Surface
 Tue, 14 Jul 2026 16:07:18 GMT
 What if we actually want to solve the "hard problem of phenomenological consciousness"
 Tue, 14 Jul 2026 15:42:27 GMT