5 Comments
User's avatar
Michael Lones's avatar

Yes, the lack of distinction between data and instruction is a fundamental issue for LLMs!

Nick Taylor's avatar

Very interesting. Making "steering" easier worries me a bit though as it could be used to introduce subtle biases. Also, did you mean Google's Gemini, rather than Gemma?

Michael Lones's avatar

Yes, good point. It could be used as a relatively accessible mechanism for developers to override trained behaviour, and perhaps is being used in this way? Certainly one owner of an AI company who might use it in this way springs to mind! Gemma is Google’s family of open weight models, derived from Gemini.

Nick Taylor's avatar

Thanks for clarifying.