The Case Against AI Control Research — LessWrong

The AI Control Agenda, in its own words: …

x The Case Against AI Control Research — LessWrong AI Control 2023 Longform Reviews AI Curated 2025 Top Fifty: 65 % 433 The Case Against AI Control Research by johnswentworth 21st Jan 2025 8 min read 85 433 The AI Control Agenda, in its own words : … 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 think no fundamental research breakthroughs are required for

saved by

• Lydia Nottingham
• Timothy Kostolansky
• Jason Hausenloy
• Jo J.
• Arjun Khandelwal
• Carolanne Jiang

related reading

• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• I think alignment work is more promising than control work — LessWronglesswrong.com
• The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably — LessWronglesswrong.com
• Reading Listblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• Many arguments for AI x-risk are wrong — AI Alignment Forumalignmentforum.org
• How might we safely pass the buck to AI? — LessWronglesswrong.com
• AI 2040: Plan Aai-2040.com
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com