top | item 45676819 (no title) Merik | 4 months ago Didn’t anthropic show that the models engage in a form of planning such that it is predicting a possible future subsequent tokens that then affects prediction of the next token: https://transformer-circuits.pub/2025/attribution-graphs/bio... discuss order hn newest ACCount37|4 months ago Sure, an LLM can start "preparing" for token N+4 at token N. But that doesn't change that the token N can't "see" N+1.Causality is enforced in LLMs - past tokens can affect future tokens, but not the other way around.
ACCount37|4 months ago Sure, an LLM can start "preparing" for token N+4 at token N. But that doesn't change that the token N can't "see" N+1.Causality is enforced in LLMs - past tokens can affect future tokens, but not the other way around.
ACCount37|4 months ago
Causality is enforced in LLMs - past tokens can affect future tokens, but not the other way around.