logoalt Hacker News

hyusapyesterday at 10:58 PM2 repliesview on HN

autoregressive generation doesn’t mean the model is myopic. the next-token distribution can already reflect a longer horizon plan for the output sequence.


Replies

npilkyesterday at 11:59 PM

Sure, but mightn’t there be several plausible long horizon plans?

Here’s an example: I had asked Claude for some music recommendations in a certain style. Part of its output was:

*Long journey tracks*

Clinic — “The Return of Evil Bill”

Guided by Voices — not really, wrong band

Silver Apples — “Oscillations”. Proto-everything, deeply repetitive, hypnotic.

So at some point there, the next token produced was “Guided” or “Guide” or whatever, and then because it can’t go back, it had to correct itself after the fact.

Reasoning/CoT have helped a lot, but I feel like small versions of this still happen all the time.

Human writing is like 90% editing.

show 1 reply
inigyoutoday at 12:32 AM

It can but it is limited because it's only got a single pass through the network to fit the entire "longer horizon plan".