michabbb on Nostr: Chain of Draft: LLMs Thinking Faster with Less Text 🚀 #Zoom researchers introduce ...

Chain of Draft: LLMs Thinking Faster with Less Text 🚀

#Zoom researchers introduce #ChainofDraft (#CoD), a new #LLM prompting method that achieves comparable accuracy to #ChainofThought while using only 7.6% of the tokens, significantly reducing cost and latency.

🧵 👇 #AI