A Mike's-Eye View of ARC's Research — Alignment Research Center
Over the past 15 months or so, ARC's technical agenda has developed quite a bit. The advent of the Matching Sampling Principle (MSP), and ideas like it, has begotten a host of concrete technical problems; progress on those problems has given us more philosophical clarity on the big picture,
Over the past 15 months or so, ARC's technical agenda has developed quite a bit. The advent of the Matching Sampling Principle (MSP), and ideas like it, has begotten a host of concrete technical problems; progress on those problems has given us more philosophical clarity on the big picture, which has led to even more technical progress. The two most recent public discussions of ARC's research (Jacob's A Bird's Eye View of ARC's Research and David's Obstacles in ARC's research agenda ) both came out before this flywheel really got spinning, and a lot of what we now consider central to the agend
saved by
related reading
- Competing with sampling — Alignment Research Centeralignment.org
- Alignment remains a hard, unsolved problem — LessWronglesswrong.com
- ARC progress update: Competing with sampling — LessWronglesswrong.com
- AGI Ruin: A List of Lethalities — LessWronglesswrong.com
- Alignment Research Centeralignment.org
- Alignment is not solved but it increasingly looks solvablealigned.substack.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- A bird's eye view of ARC's research — Alignment Research Centeralignment.org
- Shtetl-Optimized >> Blog Archive >> Theory and AI Alignmentscottaaronson.blog
- Can we safely automate alignment research? - Joe Carlsmithjoecarlsmith.com
- Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
- Why I’m optimistic about our alignment approachaligned.substack.com