[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

• The Era of Experience Paper.pdfstorage.googleapis.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• Why Tool AIs Want to Be Agent AIs · Gwern.netgwern.net
• Andrej Karpathy — AGI is still a decade awaydwarkesh.com
• Automated Weak-to-Strong Researcheralignment.anthropic.com
• Research Areas in Evaluation and Guarantees in Reinforcement Learning (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• State of Robot Learning, December 2025vedder.io
• Teaching Claude why \ Anthropicanthropic.com
• Learning through human feedback — Google DeepMinddeepmind.google
• Relaxed adversarial training for inner alignment — AI Alignment Forumalignmentforum.org
• Deep Reinforcement Learning from Human Preferencesproceedings.neurips.cc
• Should We Train Against (CoT) Monitors? — LessWronglesswrong.com