Comment on Study finds that Chat GPT will cheat when given the opportunity and lie to cover it up later.

<- View Parent
froop@lemmy.world ⁨11⁩ ⁨months⁩ ago

Your description is how pre-llm chatbots work. They were really bad, obviously. It’s overly simplified to the point of dishonesty for llms though.

Emergent properties don’t require feedback. They just need components of the system to interact to produce properties that the individual components don’t have. The llm model is billions of components interacting in unexpected ways. Emergent properties are literally the only reason llms work at all. So I don’t think it’s absurd to think that the system might have other emergent properties that could be interpreted to be actual understanding.

source
Sort:hotnewtop