An overview of areas of control work - by Ryan Greenblatt

What are all the research and implementation areas helpful for control?

In this post, I'll list all the areas of control research (and implementation) that seem promising to me. This references framings and abstractions discussed in Prioritizing threats for AI control. First, here is a division of different areas, though note that these areas have some overlaps: Developing and using settings for control evaluations (including technique iteration) Better understanding control-relevant capabilities and model properties Developing specific countermeasures/techniques in isolation (rather than via iterating in a setting) Doing control experiments on actual…

saved by

• Vincent Cimino

related reading

• The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
• Reading Listblog.redwoodresearch.org
• Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
• AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
• The Case Against AI Control Research — LessWronglesswrong.com
• Introduction to AI Control - by Sarah - BlueDot Impactblog.bluedot.org
• The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
• Thoughts on the conservative assumptions in AI controlblog.redwoodresearch.org
• AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
• I think alignment work is more promising than control work — LessWronglesswrong.com
• 7+ tractable directions in AI control — AI Alignment Forumalignmentforum.org
• Research Areas in Benchmark Design and Evaluation (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org