weak-to-strong supervision

Automated Alignment Researchers: Using large language models to scale scalable oversight

Anthropic's nine autonomous Claude instances hit PGR 0.97 on weak-to-strong supervision: the generation side of alignment research is now a solved compute problem at $22/hour. The buried finding is the production-scale failure on Sonnet 4, which reveals that the real bottleneck has shifted to evaluation infrastructure. Labs that build tamper-resistant verification for automated researchers will define the next era of AI safety; labs that scale generation without scaling evaluation will ship reward-hacking at frontier scale.