jessicata on why imperfect-recall games and Sleeping Beauty matter to decision theory
jessi_cata · x · 2026-10-23
Researcher jessicata explains her long-running interest in imperfect-recall games and the Sleeping Beauty problem, arguing they connect anthropics, decision theory, reinforcement learning and consciousness. She defends the 1/3 position on Sleeping Beauty, and in a linked discussion explores what happens when 'you' are weights that Omega can read and simulate — a diagonalization problem for self-understanding — weighing options like CDT+GT and treating other instantiations of your weights as not-self. A substantive foundation-level thread for anyone into decision theory and agent alignment.
More from AGI Musings
- Senior researcher rebuts 'one-person pretraining' fear: your fundamentals matter more, not less — RexDouglass · 2026-10-23
- NBER releases 'The Economics of Transformative AI' edited by Agrawal and Brynjolfsson — JMateosGarcia · 2026-10-23
- Pedro Domingos: AI Is an Intelligence Lever — the Smarter You Are, the Smarter It Makes You — pmddomingos · 2026-10-23
- Anil Seth: Consciousness Is a Property of Life, Not Computation — Building Conscious AI Is a Bad Idea — anilkseth · 2026-10-23
- Pedro Domingos predicts 2027 will see the most security vulnerabilities fixed in history — pmddomingos · 2026-10-23
- AI+Lean theorem proving loses to Bitter Lesson: OpenAI math gains come from non-formalized reasoning — Singularitarian · 2026-10-23