Today we’re launching Echo: Fable-level quality at ~1/3 the inference cost using open-weight models.
Echo matches or nearly matches Fable on math, science, and the coding benchmarks we currently cover, while trailing on multilingual and broader knowledge. 🧵
@_adamr_1 This is awesome super practical and impactful. Learning when not to call an LLM is such a smart approach.
Really relevant to my work around optimizing LLM usage and reducing latency/cost in production systems would love to try this out. Huge congrats on TRACER !!
We are rethinking the interaction with LLMs and just launched our beta! Join the free trial and the community we are eager for feedbacks :) https://t.co/F77Rc88t6r #LLM#ai#ArtificialIntelligence
Hey @DeGodsNFT & @y00tsNFT holders, I launched an app for a community ranking, where holders can vote for NFTs to rank them instead of relying on algorithm based ranking. So NFTs ranked by community appreciation. Let me know what you guys think of it. https://t.co/ZODBKCCdQM