

MaskLLM
public archive for AI hallucinations & reasoning failures
什麼是 MaskLLM?
MaskLLM is a community-maintained archive of documented AI failure modes: hallucinations, reasoning collapses, sycophantic reversals, jailbreaks, and more. Submissions are structured for dataset export, interpretability research, and red-team review.
截圖
?
還沒有評論,來搶沙發吧!
X 上關於 MaskLLM 的真實討論
去 X 發文


