01
follow-anything
Click-to-track video system (YOLO, BoT-SORT, SAM 2) with game-disjoint, traceable HOTA evaluation.
02
coverd-vox
An AI voice interviewer that turns structured conversations into a knowledge graph, linking each claim to its evidence in the interview. I designed the architecture.
03
RefuseBench
Open benchmark testing whether LLMs keep rules embedded in realistic policies under user pressure: 11 frontier models, 129 rules, LLM judges calibrated against blind human labels (κ 0.74–0.79). Polite multi-turn pressure raised violations ~5×. The v0.7 technical report and dataset are public (DOI 10.57967/hf/9330); ported to UK AISI Inspect Evals (under review).
