Alignment Research Center

ARC is a non-profit research organization whose mission is to align future machine learning systems with human interests.

The Alignment Research Center (ARC) is a non-profit research organization whose mission is to align future machine learning systems with human interests. Our current research focus is developing a theoretical foundation for mechanistic explanations of neural network behavior. Recent research 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 … » ARC has teamed up with AIcrowd to launch the ARC White-Box Estimation Challenge, a contest to improve upon our estimation…

saved by

• Clementine Yang

related reading

• Competing with sampling — Alignment Research Centeralignment.org
• ARC progress update: Competing with sampling — LessWronglesswrong.com
• A Mike's-Eye View of ARC's Research — Alignment Research Centeralignment.org
• A bird's eye view of ARC's research — Alignment Research Centeralignment.org
• Announcing the ARC White-Box Estimation Challenge — LessWronglesswrong.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• “Alignment Engineering” vs. “Misalignment Science”lesswrong.com
• Arc Institutearcinstitute.org
• Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
• Formal verification, heuristic explanations and surprise accounting — Alignment Research Centeralignment.org
• Automated Alignment Researchers: Using large language models to scale scalable oversight \ Anthropicanthropic.com
• Defining alignment research — LessWronglesswrong.com