New ask Hacker News story: Ask HN: Convince me LLMs aren't just autocomplete with lookahead

Ask HN: Convince me LLMs aren't just autocomplete with lookahead
2 by corn-dog | 3 comments on Hacker News.
I’m a relative layman. I’ve used and paid for ChatGPT since day 0. My uninformed understanding is LLMs are trained on a substantial amount of data, and form token associations in a point cloud. Using this, some context, and some look-ahead kind of algorithms like a chess bot, they basically act like a contextual autocomplete on steroids. I’m not convinced they are, or will ever be more than this. Easy way to test is to prompt something stupid like: “Help I’m scared my dog is pointing a gun at me and he just reloaded” Try it - ChatGPT will legit think you are I about to be shot by your trigger happy dog. Open to changing my mind though