Why FDT is hard: Newcomb variants where the agent simulates a weaker predictor
jessi_cata · x · 2026-10-05
Continuing the "Agent Simulates Predictor" thread: the author argues the problem captures what makes FDT-style theories hard. In ordinary Newcomb, where the predictor simulates you, a CDT computational functionalist can reason "I might be in a simulation, and if I am, it is causally important that I one-box" — but the picture blurs when a smarter agent simulates a weaker predictor.
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
- The Agent Simulates Predictor problem: should one-boxing survive a weaker Omega? — jessi_cata · 2026-10-05