Debunking the impossibility of utility maximization, exploring tree search and AIXI implementation
jd_pressman · x · 2026-08-23
Rebutting the claim that 'no physical object will ever maximize utility over an indefinite time horizon,' the author argues it is a category error, noting that physical laws do not seek goals. The discussion suggests that autonomous agents can be implemented using tree search algorithms, citing examples like MC-AIXI, combining LLMs with AlphaZero, or extracting reward programs from LLMs to realize VNM utility theory. The referenced paper, A Monte Carlo AIXI Approximation, introduces a principled approach for designing scalable general reinforcement learning agents based on a Monte Carlo Tree Search algorithm.
More from AGI Musings
- EU AI Safety Founder Afraid to Raise Posthumanism With Cofounders — LeviTurk · 2026-08-23
- Zuck is right: the future belongs to open systems that agents can customize — bingxu_ · 2026-08-23
- Futurist moves reverse aging prediction to 2040 due to AGI — DeryaTR_ · 2026-08-23
- Solving AI Spam: Banning Won't Work, Just Like Chain Letters — SucceededMind · 2026-08-23
- Agentic token usage 5x human on OpenRouter — AccBalanced · 2026-08-23
- AI Industry Check-in: Anthropic Wins Money and Talent, Talk Shifts to Superintelligence — RileyRalmuto · 2026-08-23