How useful is AI control? · Tracks

A calm, structured path into AI safety — technical and governance tracks, interactive demos, real writing practice, and a curated resource hub.

It might initially feel quite obvious as to why AI control would probably be good. After all, acquiring misalignment evidence, ensuring useful work of misaligned models, and having additive safety measures that generally don't interfere with alignment work, seems great. To begin this module we will Illustrate each argument against control Evaluate and attempt to remedy each argument See how useful control actually is Many of the seminal "arguments against control" lay in the following post — The Case Against AI Control Research. Your time would be well spent reading through it. Here we…

saved by

• Franca Ellerman

related reading

• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• I think alignment work is more promising than control work — LessWronglesswrong.com
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Introduction to AI Control - by Sarah - BlueDot Impactblog.bluedot.org
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• The case for ensuring that powerful AIs are controlled — AI Alignment Forumalignmentforum.org
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• Using Dangerous AI, But Safely?youtube.com