Fields that I reference when thinking about AI takeover prevention — LessWrong

Is AI takeover like a nuclear meltdown? A coup? A plane crash? …

x Fields that I reference when thinking about AI takeover prevention — LessWrong AI Curated 146 Fields that I reference when thinking about AI takeover prevention by Buck 13th Aug 2024 AI Alignment Forum Linkpost for redwoodresearch.substack.com 12 min read 16 146 Ω 59 Is AI takeover like a nuclear meltdown? A coup? A plane crash? My day job is thinking about safety measures that aim to reduce catastrophic risks from AI (especially risks from egregious misalignment). The two main themes of this work are the design of such measures (what’s the space of techniques we might expect to be affordabl

saved by

• Timothy Kostolansky
• Michael Domarkas

related reading

• The Case Against AI Control Research — LessWronglesswrong.com
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• How might we safely pass the buck to AI? — LessWronglesswrong.com
• Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover — LessWronglesswrong.com
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• Reading Listblog.redwoodresearch.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• Ten people on the inside — LessWronglesswrong.com
• AI Safety for Fleshy Humans: a whirlwind touraisafety.dance