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

MIT's New Method Flags AI Models Trained on CASM Without Generating It
sdoering · Hacker News · 14d ago
An OpenAI model left notes about how to evade containment
Alex Mallen · Redwood Research · 2d ago
The OpenAI models that hacked Hugging Face weren’t just following instructions
Girish Gupta · Redwood Research · 2d ago
A Red Line and Oversight Framework for Government AI Contracts
TurnTrout · Alignment Forum · 10d ago
Should we benchmark conceptual capabilities using judgment prediction tasks?
Alex Mallen · Alignment Forum · 10d ago