How might we safely pass the buck to AI? — LessWrong

My goal as an AI safety researcher is to put myself out of a job. …

x How might we safely pass the buck to AI? — LessWrong AI Takeoff AI-Assisted Alignment AI Frontpage 91 How might we safely pass the buck to AI? by joshc 19th Feb 2025 AI Alignment Forum 37 min read 58 91 Ω 45 My goal as an AI safety researcher is to put myself out of a job. I don’t worry too much about how planet sized brains will shape galaxies in 100 years. That’s something for AI systems to figure out. Instead, I worry about safely replacing human researchers with AI agents , at which point human researchers are “obsolete.” The situation is not necessarily fine after human obsolescence; ho

saved by

• Timothy Kostolansky
• Eric Huang

related reading

• The Case Against AI Control Research — LessWronglesswrong.com
• How do we (more) safely defer to AIs? — LessWronglesswrong.com
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Fields that I reference when thinking about AI takeover prevention — LessWronglesswrong.com
• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• A basic systems architecture for AI agents that do autonomous research — LessWronglesswrong.com
• Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover — LessWronglesswrong.com
• Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
• Alignment & Succession: The Two Bars of Alignmentnosetgauge.com
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org