News for hackers. Stuff that matters.
Re:Any insider takes on Yann LeCun's push against current ar... by numeri on Sunday March 16, 2025 @04:31AM (#43377625)
No, the person you're responding to is absolutely right. The easy test (which has been done in papers again and again) is the ability to train linear probes (or non-linear classifier heads) on the current hidden representations to predict the nth-next token, and the fact that these probes have very high accuracy.

There are no comments on this comment yet.