LulzBench
337 adversarial specimens probing how comic framing changes AI safety behaviour, with the recordings, evidence and caveats in public.
active
Tag: evaluation
3 projects
Voice Agent Hotel Lab
A fictional Hobart hotel, real voice experiments, and a listening room for the distance between sounding helpful and being right.
active
Dead Air
A voice-agent failure eval harness plus a scripted healthcare receptionist. Models endpointing, barge-in, latency and mishearing before production does.
active