AI
AI Digest
EN RU
Home Archive About RSS

#scalable-oversight

3 items

  • 8 мая Automated Weak-to-Strong Researcher: AI Agents Outperform Humans on Alignment Research Anthropic research
  • 28 июн The Verification Horizon: No Single Reward Function Works for Coding Agents at Scale Qwen (Alibaba) research
  • 9 июн Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight Rutgers University research

ai-digest.kerby.pro

© 2026 Alexei Lukin · CC BY 4.0

RSS · JSON Feed · About