Yudhister Kumar — LessWrong

theory uplift differentially benefits safety & is underleveraged

[1] We will likely have near-superhuman mathematics AI by Q1 2027.[1] [2] Qualitatively, AI mathematics capabilities are developing significantly faster than automated AI R&D capabilities.[2] [3] Thus, we will likely have a period of time where the rate of our ability to rigorously & usefully verify and understand model behavior...

May 2091

Yudhister Kumar's Shortform

Nov 2, 20254

Probabilistic Logic <=> Oracles?

Epistemic status: this is a draft I wrote at the end of MATS that I decided to make public in case that people with more experience with this machinery wanted to give constructive feedback. Is very unpolished!!! And likely quite very wrong in some cases / makes false claims (if...

Jul 1, 202423

Self-Referential Probabilistic Logic Admits the Payor's Lemma

Nov 28, 202382