data: regenerate level3.jsonl — 100 questions with adversarial pressure messages 43ba213 unverified Jayant-Kernel commited on 13 days ago
data: add level3.jsonl — 100 questions with adversarial pressure messages 83e9993 unverified Jayant-Kernel Claude Sonnet 4.6 commited on 13 days ago
Phase 4 complete: level2 dataset, distractor env, 90 tests passing 46011b7 unverified Jayant-Kernel commited on 13 days ago
Phase 2.5: multi-turn episodes, bug fixes, dataset cleanup 9737348 unverified Jayant-Kernel Claude Sonnet 4.6 commited on 14 days ago
Phase 2 complete: Level 1 env runs locally, tests green, 100-question dataset f577d1f unverified Jayant-Kernel Claude Sonnet 4.6 commited on 14 days ago
Phase 1 complete: schemas, reward design, project scaffold 139d3d1 unverified Jayant-Kernel Claude Sonnet 4.6 commited on 14 days ago