EditLens: Quantifying the extent of AI editing in text (2025)
28 points by horseradish
by andyfilms1
3 subcomments
I genuinely think any ML approach to detecting ML will always be unreliable. Models can be intentionally poisoned or tricked, and there is a lot of incentive from AI users to do so. It will always be a losing battle against a moving target.
I think in the long run, deterministic algorithmic approaches with complex pipelines will be needed.
by
0 subcomment
by deminature
1 subcomments
This research has been commercialized by a company called Pangram, who sells access to AI detection as a service, via an API.