Post

this isn't cheating, and it's not "absolutely bizarre"! this is just how LLMs work. they are improv machines. they do not have any sense of truth or fiction bc they don't "know" anything. they can't even "know" if they "looked" at an "image." this is totally unsurprising

"seeing" something that isn't there is literally the definition of "hallucination" so i think these researchers had to know what they were doing & were doing it on purpose

the models generally "championed" for radiology are typically specialized, not commercial chatbots aka "frontier models" they still do the stupidest shit — like correlating diagnosis based on which hospital name was on the image — bc there's no such thing as artificial *intelligence*

I’m a little surprised that people don’t understand ai/ml algorithms to be pattern finding machines. And they might not find the patterns you expect! (It might be more accurate to call them correlation finding machines)

i wouldn't even say "pattern-finding" but they can be reasonably good at surfacing/extruding them ~accidentally~ hehe yeah, idk why people who ought to know better treat llms like universal tools. i know it's marketed that way but that literally harms the perception of the product? it's weird

I meant pattern matching in a more mathematical sense, which is problematic because “pattern” means something different in common use (hence the correlation comment)

well maybe these researchers really are the dumb babies they sound like, bc llms don't EVER work by "diving into the data" and using "probability" that implies the llms analyze and calculate. and they can't! responses are dictated by statistical correlations between TOKENS in the CORPUS