Subagents, akrasia, and coherence in humans — LessWrong
In my previous posts, I have been building up a model of mind as a collection of subagents with different goals, and no straightforward hierarchy. Th…
x Subagents, akrasia, and coherence in humans — LessWrong Multiagent Models of Mind Akrasia Subagents Cached Thoughts Internal Family Systems Robust Agents Slack Curated 146 Subagents, akrasia, and coherence in humans by Kaj_Sotala 25th Mar 2019 20 min read 31 146 In my previous posts , I have been building up a model of mind as a collection of subagents with different goals, and no straightforward hierarchy. This then raises the question of how that collection of subagents can exhibit coherent behavior: after all, many ways of aggregating the preferences of a number of agents fail to create c
Explore this link on the map →related reading
- The hot mess theory of AI misalignment: More intelligent agents behave less coherently | Jascha’s blogsohl-dickstein.github.io
- Building up to an Internal Family Systems model — LessWronglesswrong.com
- Managed vs Unmanaged Agency — LessWronglesswrong.com
- llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com
- ⿻ Symbiogenesis vs. Convergent Consequentialism — LessWronglesswrong.com
- Don’t Build Multi-Agents | Cognitioncognition.ai
- Irrationality as a Defense Mechanism for Reward-hacking — LessWronglesswrong.com
- Arjun Virkarjunvirk.com
- Reward Is Not Enough — LessWronglesswrong.com
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com