[AN #70]: Agents that help humans who are still learning about their own preferences — LessWrong

Find all Alignment Newsletter resources here. In particular, you can sign up, or look through this spreadsheet of all summaries that have ever been i…

x [AN #70]: Agents that help humans who are still learning about their own preferences — LessWrong Alignment Newsletter Newsletters AI Frontpage 16 [AN #70]: Agents that help humans who are still learning about their own preferences by Rohin Shah 23rd Oct 2019 Alignment Newsletter AI Alignment Forum 11 min read 0 16 Ω 14 Find all Alignment Newsletter resources here . In particular, you can sign up , or look through this spreadsheet of all summaries that have ever been in the newsletter. I'm always happy to hear feedback; you can send it to me by replying to this email. Audio version here (may

saved by

• Sheikh Abdur Raheem Ali

related reading

• Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
• Reward is not the optimization target — LessWronglesswrong.com
• [AN #159]: Building agents that know how to experiment, by training on procedurally generated games — AI Alignment Forumalignmentforum.org
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Models Don't "Get Reward" — LessWronglesswrong.com
• Self-Other Overlap: A Neglected Approach to AI Alignment — LessWronglesswrong.com
• Auditing language models for hidden objectives — LessWronglesswrong.com
• Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• Automated Alignment is Harder Than You Think — LessWronglesswrong.com