100% - although it is stunning to see since most LLMs get CORS questions right (which is surprising since they trained on all sorts of incorrect data).
100% - although it is stunning to see since most LLMs get CORS questions right (which is surprising since they trained on all sorts of incorrect data).
Maybe it’s like that trick where if a thousand people guess the amount of beans in a jar almost all of them will be wrong but their average will be very close to, if not, correct.
they probably weight documentation higher
They're applying trust factors similar to PageRank.
Possibly, but at a semantic level.
I think many (most?) have preferred sources. I would weight Wikipedia and MDN higher than Snurk Grubble's blog in training, no matter what the topic.
Also, you can count on most developers to reach the documentation only as a last resort, and try every random blog first.
They look for latent structure in the data.
It's probably trained more on fixes on incorrect CORS than the problems