Automating Auditing Games of Sandbagging
Collection
The 16 validated sandbagging model organisms (Qwen3-8B LoRAs) from the paper. Gated: access for auditing research, reviewed manually. • 16 items • Updated
ChristopherT
darklord1611
AI & ML interests
None yet
Recent Activity
updated a collection 3 days ago
Automating Auditing Games of Sandbagging updated a collection 3 days ago
Automating Auditing Games of Sandbagging updated a collection 3 days ago
Automating Auditing Games of SandbaggingOrganizations
updated a
collection 3 days ago
published 4
models 3 days ago