An overview of areas of control work - by Ryan Greenblatt
blog.redwoodresearch.org · 8,098 words · saved by 1 readers
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
related reading
- [2408.02565] Reasons to Doubt the Impact of AI Risk Evaluationsarxiv.org
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Research Areas in AI Control (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- Reading Listblog.redwoodresearch.org
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- AI Control: Improving Safety Despite Intentional Subversion — AI Alignment Forumalignmentforum.org
- 7+ tractable directions in AI control — AI Alignment Forumalignmentforum.org
- The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
- 7+ tractable directions in AI control — LessWronglesswrong.com
- I think alignment work is more promising than control work — LessWronglesswrong.com