Post

"Never hallucinate or make anything up." yes, you can just demand that the LLM not make errors that's definitely how the technology works

There's actually evidence that this reduces hallucinations/errors. arxiv.org/abs/2304.13734 gist.github.com/yoavg/4e4b48...

That's not an internal state

What do you mean?

An internal state requires an internality.

Hidden layers aren't inside anything, they're just layers.

Ok but why are you telling me this? My point was that prompting "Never hallucinate or make anything up" actually helps. I never made any claims about hidden layers being inside of anything. I know how NNs work...

Internal state just a technical term that refers to hidden layer activations, it has nothing to do with humans.

The field should choose less anthropomorphising technical terms.

The paper also talks about the model having an "internal notion". Is notion also an industry term?