zlacker

It's not obvious to me whether we should count these errors as failures of intelligence or failures of perception. There's at least a loose analogy to optical illusion, which can fool humans quite consistently. Now you might say that a human can usually figure out what's going on and correctly identify the illusion, but we have the luxury of moving our eyes around the image and taking it in over time, while the model's perception is limited to a fixed set of unchanging tokens. Maybe this is relevant.

(Note I'm not saying that you can't find examples of failures of intelligence. I'm just questioning whether this specific test is an example of one).

>>qnleig+(OP)
I am having trouble understanding the distinction you’re trying to make here. The computer has the same pixel information that humans do and can spend its time analyzing it in any way it wants. My four-year-old can count the legs of the dog (and then say “that’s silly!”), whereas LLMs have an existential crisis because five-legged-dogs aren’t sufficiently represented in the training data. I guess you can call that perception if you want, but I’m comfortable saying that my kid is smarter than LLMs when it comes to this specific exercise.

>>cyanma+v1
Your kid, it should be noted, has a massively bigger brain than the LLM. I think the surprising thing here maybe isn't that the vision models don't work well in corner cases but that they work at all.

Also my bet would be that video capable models are better at this.

>>cyanma+v1
LLMs can count other objects, so it's not like they're too dumb to count. So a possible model for what's going on is that the circuitry responsible for low-level image recognition has priors baked in that cause it to report unreliable information to parts that are responding for higher-order reason.

So back to the analogy, it could be as if the LLMs experience the equivalent of a very intense optical illusion in these cases, and then completely fall apart trying to make sense of it.