Why powerful AIs could cooperate in one-shot prisoner's dilemmas: open-source code proofs
tszzl · x · 2026-11-03
azsantosk highlights why Eliezer Yudkowsky believes powerful AIs may cooperate even in one-shot prisoner's dilemmas: Yudkowsky literally proved in a paper that such cooperation is possible in general for two different AI systems, as long as both can read each other's source code (link included). chrislakin quips it 'helps me understand George Hotz so much.' A revival of the classic Löb/program-equilibrium discussion in AI cooperation theory.
More from AGI Musings
- A model better at editing its own weights is a very tight RSI loop — rickasaurus · 2026-11-03
- After visiting Chinese AI labs: the gap with US frontier labs is widening — pstAsiatech · 2026-11-03
- The Blindsight 'Conspiracy': Are Blindsight Patients Just Pretending? — theshawwn · 2026-11-03
- Paul Graham: the scariest part is calling this a normal year — paulg · 2026-11-03
- Is 'Higher Intelligence' Just What Takes Humans Longer to Learn? — GregCook2011 · 2026-11-03
- kalomaze: In-context learning is an incidental byproduct of next-token prediction, not deliberate design — kalomaze · 2026-11-03