←back to thread

S1: A $6 R1 competitor?

(timkellogg.me)
851 points tkellogg | 4 comments | | HN request time: 0.001s | source
Show context
mtrovo ◴[] No.42951263[source]
I found the discussion around inference scaling with the 'Wait' hack so surreal. The fact such an ingeniously simple method can impact performance makes me wonder how many low-hanging fruit we're still missing. So weird to think that improvements on a branch of computer science is boiling down to conjuring the right incantation words, how you even change your mindset to start thinking this way?
replies(16): >>42951704 #>>42951764 #>>42951829 #>>42953577 #>>42954518 #>>42956436 #>>42956535 #>>42956674 #>>42957820 #>>42957909 #>>42958693 #>>42960400 #>>42960464 #>>42961717 #>>42964057 #>>43000399 #
ascorbic ◴[] No.42954518[source]
I've noticed that R1 says "Wait," a lot in its reasoning. I wonder if there's something inherently special in that token.
replies(2): >>42954757 #>>42959520 #
1. katzenversteher ◴[] No.42959520[source]
I bet a token like "sht!", "f*" or "damn!" would have the same or even stronger effect but the LLM creators would not like to have the users read them
replies(3): >>42959617 #>>42960035 #>>42960519 #
2. lodovic ◴[] No.42959617[source]
I think you're onto something, however, as the training is done through on text and not actual thoughts, it may take some experimentation to find these stronger words.
3. ascorbic ◴[] No.42960035[source]
Maybe, but it doesn't just use it to signify that it's made a mistake. It also uses it in a positive way, such as it's had a lightbulb moment. Of course some people use expletives in the same way, but that would be less common than for mistakes.
4. raducu ◴[] No.42960519[source]
It's literally in the article, they measured it and wait was the best token