(My understanding of) What Everyone in Technical Alignment is Doing and Why - LessWrong

Epistemic Effort: ~75 hours of work put into this document …

x (My understanding of) What Everyone in Technical Alignment is Doing and Why — LessWrong Research Agendas AI Alignment Fieldbuilding AI Curated 415 (My understanding of) What Everyone in Technical Alignment is Doing and Why by Thomas Larsen , elifland 29th Aug 2022 AI Alignment Forum 45 min read 90 415 Ω 95 Epistemic Status: My best guess Epistemic Effort: ~75 hours of work put into this document Contributions: Thomas wrote ~85% of this, Eli wrote ~15% and helped edit + structure it. Unless specified otherwise, writing in the first person is by Thomas and so are the opinions. Thanks to Mirand

related reading

• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• Study Guide — LessWronglesswrong.com
• Tips for Empirical Alignment Research — AI Alignment Forumalignmentforum.org
• Current AIs seem pretty misaligned to me — LessWronglesswrong.com
• Defining alignment research — LessWronglesswrong.com
• PSA: Almost nobody is directly working on superintelligent alignment — LessWronglesswrong.com
• Model Organisms of Misalignment: The Case for a New Pillar of Alignment Research — AI Alignment Forumalignmentforum.org
• Automated Alignment is Harder Than You Think — LessWronglesswrong.com
• I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWronglesswrong.com
• I think alignment work is more promising than control work — LessWronglesswrong.com
• Thoughts on the Alignment Implications of Scaling Language Models | Leo Gaobmk.sh