Ten people on the inside - by Buck Shlegeris

A scary scenario that's worth planning for

Ten people on the inside A scary scenario that's worth planning for Buck Shlegeris Jan 28, 2025 16 Share (Many of these ideas developed in conversation with Ryan Greenblatt) In a shortform , I described some different levels of resources and buy-in for misalignment risk mitigations that might be present in AI labs: *The “safety case” regime.* Sometimes people talk about wanting to have approaches to safety such that if all AI developers followed these approaches, the overall level of risk posed by AI would be minimal. (These approaches are going to be more conservative than will probably be fe

related reading

• Ten people on the inside — LessWronglesswrong.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Plans A, B, C, and D for misalignment risk — LessWronglesswrong.com
• Plans A, B, C, and D for misalignment riskblog.redwoodresearch.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• The Case Against AI Control Research — LessWronglesswrong.com
• Reading Listblog.redwoodresearch.org
• Ten AI safety projects I'd like people to work onthirdthing.ai
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com