Why we're working on white box control
Introduces AISI's white box control research, which monitors or steers model internals to detect sandbagging, and reports preliminary progress on that detection.
Research
UK AI Security Institute
The UK government’s AI Security Institute: evaluations, red-teaming and research on frontier AI risks. aisi.gov.uk
Focus All
Topic Interpretability
Source UK AISI · 1
Date Any time
1 item