A Mike's-Eye View of ARC's Research

·ARC··

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&...

Read full article →

Related Articles

CoT controllability evals seem very under-elicited
Jozdien · Alignment Forum · 10h ago
MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 2mo ago
When a Claude Judge Recognizes the Hack but Still Says HONEST
JulesRoussel01 · LessWrong · 1d ago
Astra can do a concerning amount with no chain of thought
Neel Nanda · Alignment Forum · 2d ago
Item Response Theory for AI Safety
Joshua Fonseca Rivera · LessWrong · 1mo ago