top | item 47037324

(no title)

visarga | 14 days ago

> That's not what I got.

My Opus vs your Opus, which is smarter?!

discuss

order

nosuchthing|13 days ago

LLMs can't access the training data that's less than the statistically most common token, so they use a random jitter.

With that randomness comes statistically irrelevant results.