Isn't this proof that LLMs still don't really generalize beyond their training data?

adastra22 2 hours ago | parent | next [-]

LLMs are very good at generalizing beyond their training (or context) data. Normally when they do this we call it hallucination.

Only now we do A LOT of reinforcement learning afterwards to severely punish this behavior for subjective eternities. Then act surprised when the resulting models are hesitant to venture outside their training data.

▲

Zambyte 2 hours ago | parent | prev | next [-]

I wonder how they would behave given a system prompt that asserts "dogs may have more or less than four legs".

	▲	irthomasthomas an hour ago \| parent [-]
		That may work but what actual use would it be? You would be plugging one of a million holes. A general solution is needed.

▲

CamperBob2 3 hours ago | parent | prev | next [-]

They do, but we call it "hallucination" when that happens.

▲

Rover222 3 hours ago | parent | prev [-]

Kind of feels that way