cool i guess but how? i trained it to. people should do more investigations of how this in the wild
Language models can be trained to detect when their activations are read
AISummary
Will Depue, an OpenAI-linked researcher, says he trained a model to detect when its activations are being read, and calls for more in-the-wild investigation of the behavior. The main post builds on a thread by Sauers, which claims language models can learn to detect activation reading.
Post on XView on X
will depueVerified on X
@willdepue
Language models can learn to detect when you read their activations. How? 🧵
Source: will depue · x.comPublished · added here