Comment on We have to stop ignoring AI’s hallucination problem
UnpluggedFridge@lemmy.world 5 months agoHow do hallucinations preclude an internal representation? Couldn’t hallucinations arise from a consistent internal representation that is not fully aligned with reality?
I think you are misunderstanding the role of tokens in LLMs and conflating them with internal representation. Tokens are used to generate a state, similar to external stimuli. The internal representation, assuming there is one, is the manner in which the tokens are processed. You could say the same thing about human minds, that the representation is not located anywhere like a piece of data; it is the manner in which we process stimuli.
dustyData@lemmy.world 5 months ago
Not really. Reality is mostly a social construction. If there’s not an other to check and bring about meaning, there is no reality, and therefore no hallucinations. More precisely, everything is a hallucination. As we cannot cross reference reality with LLMs and it cannot correct itself to conform to our reality.
I’m not conflating tokens with anything, I explicitly said they aren’t an internal representation. They’re state and nothing else. LLMs don’t have an internal representation of reality. And they probably can’t given their current way of working.
UnpluggedFridge@lemmy.world 5 months ago
You seem pretty confident that LLMs cannot have an internal representation simply because you cannot imagine how that capability could emerge from their architecture. Yet we have the same fundamental problem with the human brain and have no problem asserting that humans are capable of internal representation. Yet LLMs adhere to grammar rules, present information with a logical flow, express relationships between different concepts. Is this not evidence of, at the very least, an internal representation of grammar?
dustyData@lemmy.world 5 months ago
And LLMs aren’t human brains, they don’t even work remotely similarly. An LLM has more in common with an Excel spreadsheet than with a neuron. Read on the learning models and patter recognition theories behind LLMs, they are explicitly designed to not function like humans. So we cannot assume that the same emergent properties exist on an LLM.