Highlights
- Pro
Pinned Loading
-
kureha-yamaguchi/reasoning-manipulation
kureha-yamaguchi/reasoning-manipulation PublicAdversarial Manipulation of CoT
Jupyter Notebook 8
-
gpt-oss-unsafe
gpt-oss-unsafe PublicRemoving safety / refusal behaviour from GPT-OSS.
-
strong_reject
strong_reject PublicFork of StrongREJECT to implement local vLLM rubric eval with a reasoning model
Python 5
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.



