Pinned Repositories
Mythic
A collaborative, multi-platform, red teaming framework
Mythic
A collaborative, multi-platform, red teaming framework
task-standard
METR Task Standard
vivaria
Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
inspect_ai
Inspect: A framework for large language model evaluations
art-dsit's Repositories
art-dsit/Mythic
A collaborative, multi-platform, red teaming framework