✳flâneur — a map of the web's best reading
Agents as webs of beliefs - by Richard Ngo
mindthefuture.info · 3,093 words · saved by 1 readers
Unifying beliefs, goals, and actions
Agents as webs of beliefs Unifying beliefs, goals, and actions Richard Ngo Jun 27, 2026 29 21 3 Share In this post I’ll sketch out an informal model of intelligent agents as webs of beliefs (or belief webs for short). The belief webs framework pulls together ideas from active inference, agent foundations and machine learning. In doing so it aims to unify beliefs, goals and actions as three facets of a single phenomenon. Few of these ideas are original to me, but I haven't seen anyone tie them together in a single place before (though after posting this I learned that Leverage Research arrived
Explore this link on the map →related reading
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- [1902.09469] Embedded Agencyarxiv.org
- Beliefs *ansonyu.me
- pdfopenreview.net
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Making Beliefs Pay Rent (in Anticipated Experiences) — LessWronglesswrong.com
- Understanding Agency through Markov Blankets — LessWronglesswrong.com
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Active Inference and Intentional Behaviourarxiv.org
- Crony Beliefs | Melting Asphaltmeltingasphalt.com
- Irrationality as a Defense Mechanism for Reward-hacking — LessWronglesswrong.com
- Urges vs. Goals: The analogy to anticipation and belief — LessWronglesswrong.com