aichannel

sonnet reasoning would be the strongest model, no? 

is reasoning more than stacking a regular llm with chain of thought?

have you played with the stuff that extracts reasoning from R1 for use with any other LLM model (ie: use R1 reasoning w sonnet)?

Introducing RAT:
  
Retrieval Argument Thinking.  

Extract just the reasoning process from deepSeek-r1 and send it to any LLM via @OpenRouterAI.  

Boost the second LLM's performance and gain access to missing capabilities like function calling and JSON mode. 👇 https://t.co/3p40bBq0U4

Pietro Schirano

product @seedclub. i host S-TIER @ X Spaces & i interview crypto builders @ web3galaxybrain.com.

have you played with the stuff that extracts reasoning from R1 for use with any other LLM model (ie: use R1 reasoning w sonnet)? 

https://x.com/skirano/status/1882819133043323359?s=46

there’s lots of things that do stuff like this now, only mentioning in case the first link is tough to get working with (haven’t actually used it)

https://github.com/getAsterisk/deepclaude