←back to thread

S1: A $6 R1 competitor?

(timkellogg.me)
851 points tkellogg | 1 comments | | HN request time: 0.199s | source
Show context
bloomingkales ◴[] No.42949616[source]
If an LLM output is like a sculpture, then we have to sculpt it. I never did sculpting, but I do know they first get the clay spinning on a plate.

Whatever you want to call this “reasoning” step, ultimately it really is just throwing the model into a game loop. We want to interact with it on each tick (spin the clay), and sculpt every second until it looks right.

You will need to loop against an LLM to do just about anything and everything, forever - this is the default workflow.

Those who think we will quell our thirst for compute have another thing coming, we’re going to be insatiable with how much LLM brute force looping we will do.

replies(3): >>42955281 #>>42955806 #>>42956482 #
gyomu ◴[] No.42956482[source]
> If an LLM output is like a sculpture, then we have to sculpt it. I never did sculpting, but I do know they first get the clay spinning on a plate.

That’s pottery, not sculpture. Traditionally in sculpture you start from a block of marble or wood, but you can also make sculptures of cast bronze or welded steel (or clay, but you don’t use a spinning plate).

replies(1): >>42957923 #
1. bloomingkales ◴[] No.42957923[source]
Thank you for the clarification. I wanted to use some kind of visual to show the model in a loop. Otherwise, I’d just have to say explicitly that the sculptor is the one in the loop, as in the person will not stop chiseling. It’s in this infinite chiseling that we get our answers (same thing as finding a limit in calculus as it approaches infinity, we will never get the discrete answer, but we will get infinitely close enough to label a discrete point confidently).

In other words, we fly as close to the sun as possible and get our measurements :)