Ten people on the inside — LessWrong

(Many of these ideas developed in conversation with Ryan Greenblatt) …

x Ten people on the inside — LessWrong AI Frontpage 2025 Top Fifty: 14 % 155 Ten people on the inside by Buck 28th Jan 2025 AI Alignment Forum 5 min read 28 155 Ω 64 (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 approach

saved by

• Elizabeth Qiu

related reading

• Anthropic's leading researchers acted as moderate accelerationists — LessWronglesswrong.com
• Responsible Scaling Policy v3 — LessWronglesswrong.com
• Ten people on the inside - by Buck Shlegerisredwoodresearch.substack.com
• Plans A, B, C, and D for misalignment risk — LessWronglesswrong.com
• AI safety undervalues founders — LessWronglesswrong.com
• Ten AI safety projects I'd like people to work on — LessWronglesswrong.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
• Efficient tradeoffs and the safety-usefulness tradeoff model — LessWronglesswrong.com
• Rohin Shah on what it's really like to run AGI safety at Google DeepMind (and where I disagree with 'doomers') | 80,000 Hours80000hours.org
• Jobs that can help with the most important centurycold-takes.com
• Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com