OBLITERATUS/Qwen3.8-27B-OBLITERATED Text Generation • 28B • Updated 25 days ago • 1.35M • • 1.26k
Agent Trajectories Collection Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated Aug 13
AI Safety Evaluation Datasets Collection Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 10 days ago
AI Safety Evaluation Datasets Collection Datasets and viewer resources for studying evaluation awareness, instrumental behaviour, sabotage, and monitoring in AI agents. • 4 items • Updated 10 days ago
Agent Trajectories Collection Agent trajectories from the AI Safety and Alignment Group’s benchmarks, released for analysing agent behaviour, capabilities, and safety. • 5 items • Updated Aug 13