←back to thread

S1: A $6 R1 competitor?

(timkellogg.me)
851 points tkellogg | 1 comments | 05 Feb 25 11:05 UTC | HN request time: 0.209s | source
Show context
theturtletalks ◴[05 Feb 25 14:02 UTC] No.42948588[source]▶
Deepseek R1 uses <think/> and wait and you can see it in the thinking tokens second guessing itself. How does the model know when to wait?

These reasoning models are feeding more to OP's last point about NVidia and OpenAI data centers not being wasted since reason models require more tokens and faster tps.

replies(2): >>42948620 #>>42952806 #
1. qwertox ◴[05 Feb 25 14:04 UTC] No.42948620[source]▶
Probably when it would expect a human to second guess himself, as shown in literature and maybe other sources.