The case for ensuring that powerful AIs are controlled — LessWrong

In this post, we argue that AI labs should ensure that powerful AIs are controlled. That is, labs should make sure that the safety measures they appl…

x The case for ensuring that powerful AIs are controlled — LessWrong Best of LessWrong 2024 AI Control Redwood Research Deceptive Alignment AI Curated 290 The case for ensuring that powerful AIs are controlled by ryan_greenblatt , Buck 24th Jan 2024 AI Alignment Forum 34 min read 74 290 Ω 114 In this post, we argue that AI labs should ensure that powerful AIs are controlled . That is, labs should make sure that the safety measures they apply to their powerful models prevent unacceptably bad outcomes, even if the AIs are misaligned and intentionally try to subvert those safety measures. We thin

saved by

• Elizabeth Qiu
• Shubham Chandel
• Asher P
• Lydia Nottingham
• Vincent Cheng
• Emil Ryd
• Jason Hausenloy
• Jo J.
• Dillon Nguyen
• Anastasia Wei
• Anaya Mandal

related reading

• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• The Case Against AI Control Research — LessWronglesswrong.com
• The case for ensuring that powerful AIs are controlled — AI Alignment Forumalignmentforum.org
• Reading Listblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• Introduction to AI Control - by Sarah - BlueDot Impactblog.bluedot.org
• [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
• Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• Dario Amodei — The Adolescence of Technologydarioamodei.com
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com