1611.08219
arxiv.org · 6,511 words · saved by 1 readers
N/A
The Off-Switch Game Dylan Hadfield-Menell1 and Anca Dragan1 and Pieter Abbeel1,2,3 and Stuart Russell1 1 University of California, Berkeley, 2 OpenAI, 3 International Computer Science Institute (ICSI) {dhm, anca, pabbeel, russell}@cs.berkeley.edu Abstract…
saved by
related reading
- Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
- Embedded Agency (full-text version) — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- [1902.09469] Embedded Agencyarxiv.org
- TechnicalAgenda.pdfintelligence.org
- Reward Is Not Enough — LessWronglesswrong.com
- Human-Compatible Artificial Intelligencepeople.eecs.berkeley.edu
- Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
- Towards a scale-free theory of intelligent agencymindthefuture.info
- [1605.03142] Self-Modification of Policy and Utility Function in Rational Agentsarxiv.org
- Why are AI agents lying, cheating and coordinating?yoshuabengio.org
- How might we safely pass the buck to AI? — LessWronglesswrong.com