MaskLLM
public archive for AI hallucinations & reasoning failures
89 followers
public archive for AI hallucinations & reasoning failures
89 followers
MaskLLM is a community-maintained archive of documented AI failure modes—hallucinations, reasoning collapses, sycophantic reversals, jailbreaks, and more.
Submissions are structured and published as a public dataset on HuggingFace, designed for interpretability researchers and red teams.
All entries require a reproducible prompt, the model's response, and a failure classification.
This is the 2nd launch from MaskLLM. View more
MaskLLM
Launching today
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.
Free
Launch Team
MaskLLM