Solomonoff induction mirrors how intelligence works — but is physically impossible
burny_tech · x · 2026-09-27
Kfir Dolev offers a theoretical observation: Solomonoff induction looks a lot like how intelligence really works — predicting by keeping every hypothesis weighted by simplicity — but it is impossible for any physically finite-compute agent to implement. A concise take on the gap between ideal Bayesian inference and real intelligence.
More from AGI Musings
- Prediction: AIs with robust autobiographical memory will truly be conscious — yeastsplainer · 2026-09-27
- Ex-OpenAI/Anthropic pretraining researcher quits, slams labs' superintelligence race — Aiden_Tech_Ai · 2026-09-27
- Worker argues AI should replace much of middle management's approval busywork — sporty_outlook · 2026-09-27
- Ethan Mollick Quips That Multimodal LLMs With Tools Are 'Almost Like Artificial General Intelligence' — emollick · 2026-09-27
- Google's Copyright Argument Accidentally Concedes Generative AI Output Is Unpredictable — AlexTensor · 2026-09-27
- Digital Consciousness Model Paper: Evidence Against 2024 LLM Consciousness Is Not Decisive — burny_tech · 2026-09-27