Multi-Turn
Papers on multi-turn degradation, recovery, and interaction-centric failure analysis.
Tag: Evaluation
AI Safety Research Collaborations
Research work on self-preservation propensity, emergent misalignment, and character training.
Emergent Misalignment
Selected reading on narrow finetuning and broad behavioral change.
Evaluation
Long-form references on benchmarks, measurement, and what evaluations actually test.
Medmarks
Contributed to an open-source benchmark suite for medical LLM capabilities.