Highlights
- Pro
Popular repositories Loading
-
-
-
AIAE-AbliterationBench
AIAE-AbliterationBench PublicForked from gpiat/AIAE-AbliterationBench
The entry for [Team Blue 2, Electric Boogaloo] at the January 2025 AI-Plans AI Alignment Evals Hackathon. It uses Abliteration (Arditi et al) as a base for benchmarking model resilience to residual…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.