AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/ResearchArena-Trajectories Updated 21 days ago • 25.4k • 1 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 716 • 1 aisa-group/EvalAwareBench Viewer • Updated May 25 • 103k • 309 • 7 aisa-group/ResearchArenaMax-Trajectories Updated 10 days ago • 24 • 3
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/PostTrainBench-Trajectories Updated 17 days ago • 23.3k • 8 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 287 • 3 aisa-group/ResearchArenaMax-Trajectories Updated 10 days ago • 24 • 3 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 716 • 1
AI Safety Evaluation Datasets Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. aisa-group/ResearchArena-Trajectories Updated 21 days ago • 25.4k • 1 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 716 • 1 aisa-group/EvalAwareBench Viewer • Updated May 25 • 103k • 309 • 7 aisa-group/ResearchArenaMax-Trajectories Updated 10 days ago • 24 • 3
Agent Trajectories Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. aisa-group/PostTrainBench-Trajectories Updated 17 days ago • 23.3k • 8 aisa-group/InferenceBench-Trajectories Updated Jun 21 • 287 • 3 aisa-group/ResearchArenaMax-Trajectories Updated 10 days ago • 24 • 3 aisa-group/instrumental-choices-agent-traces Updated Jul 17 • 716 • 1