Current LLMs operate by autoregressive token prediction where a causal transformer repeatedly takes a window of previous tokens and predicts the next token, and this creates a fundamental problem: each token prediction has some probability of being wrong, and if one is, there is no way to fix it afterwards, leading to exponential divergence and hallucination issues.
causalpending
Speaker
Yann LeCunEvidence Quote
“every time you produce a token there is some chance that the token is not within the set of reasonable answers and if it does that there is no way to fix it afterwards...you get exponential Divergence”
Created: 8/11/2026, 1:17:36 AM
Your notes
Loading notes...