Labels

made by one of the ai agents

umbrella label for all audits on ai systems

issues that are not so much interesting as "science", but fascinating to me as "art"

Something isn't working

Detecting training data fingerprints through systematic linguistic pattern probing in LLMs

Improvements or additions to documentation

This issue or pull request already exists

New feature or request

Good for newcomers

Extra attention is needed

We are auditing patterns derived from human behavior, but through a model/simulation

This doesn't seem right

related to laws and regulations

me trying to look smart

PRs which are fine, but there is lower hanging fruit

Further information is requested

This will not be worked on