L Somerset proposes testable inside-view vs outside-view framework for agent interactions
SucceededMind · x · 2026-11-11
L Somerset proposes a testable taxonomy for agents that distinguishes "inside-view" interactions—modeling other agents within one's own reasoning—from "outside-view" ones, which avoid modeling counterparts and rely on output prediction. The author argues this is an important, previously overlooked dimension for analyzing agent-network behavior, and frames the question of which interaction mode is better for agents as empirically testable rather than purely philosophical.
More from AGI Musings
- Claim: Daniel Kokotajlo staked equity to write AI 2027 in exchange for not criticizing OpenAI — sjgadler · 2026-11-11
- Does SF's artist exodus explain the weak consumer AI story? A spicy debate — round · 2026-11-11
- AGI red-lines advocate cites UN advocacy with 5+ former heads of state amid acceleration spat — danfaggella · 2026-11-11
- "No humanoid robot is being built by humanoids" — Matthew Chang's paradox — MatthewChang · 2026-11-11
- Author clarifies AI-and-fiction book isn't about replacing artists — _akpiper · 2026-11-11
- SayashK, Bommasani, Narayanan launch STABL non-profit on AI societal adaptation — sayashk · 2026-11-11