The Agent Simulates Predictor problem: should one-boxing survive a weaker Omega?
jessi_cata · x · 2026-10-05
A discussion of the classic LessWrong problem "Agent Simulates Predictor": when Omega is a weaker predictor the agent can simulate by decision time, is one-boxing still correct, and what's the right algorithm? Participants argue existing decision-theoretic frameworks don't apply cleanly to agent pairs with large intelligence gaps.
Related event: Debate Rekindled Over Decision Theory When Agents Simulate Predictors(4 posts)→
More from Research
- ICML 2026 proceedings go live on PMLR as Volume 306 from Seoul conference — lawrennd · 2026-10-05
- Neuroscientist Anil Seth's TED talk: current AI won't become conscious — we're seeing faces in clouds — anilkseth · 2026-10-05
- CMU ships cua-speedrun: standardized benchmark finally measures computer-use agent speed and cost — rsalakhu · 2026-10-05
- TernaryQuench: open-source ternary quantization trainer for Qwen3 with MLX export — casper_hansen_ · 2026-10-05
- Xaira unveils AI drug discovery platform: 10x medicines goal, early results on hard GPCR target — BoWang87 · 2026-10-05
- Bergson: open-source library unifies data attribution methods to study LLM generalization and misalignment — zetalyrae · 2026-10-05