Phind Model beats GPT-4 at coding, with GPT-3.5 speed and 16k context(phind.com)
793 points by rushingcreek | 316 comments
Phind announces its own coding-focused LLM, built on CodeLlama-34B fine-tunes, claiming GPT-4-level coding answers at 5x speed with 16k context.






![Screenshot of researchgate.net: The Professionalization of Cryptology in Sixteenth-Century Venice (2018) [pdf]](https://hn.urlbox.com/shots/renders/2023/12/12/b5178e03-d30a-4387-afe6-d2092fd62a52.jpg)