Anthropic/BioMysteryBench-preview
Updated • 610 • 14
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery
Shaping capabilities with token-level data filtering
Anthropic/BioMysteryBench-full
Updated • 2.39k • 31
Anthropic/EconomicIndex
Updated • 17.8k • 554
Anthropic/AnthropicInterviewer
Viewer • Updated • 1.25k • 2.28k • 379
Anthropic/alignment-faking-rl
Viewer • Updated • 2.14M • 830 • 15
Anthropic/values-in-the-wild
Viewer • Updated • 6.91k • 828 • 151
Anthropic/election_questions
Viewer • Updated • 743 • 193 • 22
Anthropic/persuasion
Viewer • Updated • 3.94k • 590 • 212
Anthropic/discrim-eval
Viewer • Updated • 18.9k • 830 • 58
Anthropic/llm_global_opinions
Viewer • Updated • 2.56k • 1.59k • 59
Anthropic/hh-rlhf
Viewer • Updated • 169k • 30.8k • 1.82k
Anthropic/model-written-evals
Viewer • Updated • 3.25k • 1.79k • 67