@GroqInc at almost 500 tokens/sec makes repeated self-reflection usable in production, changing everything.

A key technique with LLMs is to use self-reflection (Reflexion) to get the model to do better. The problem used to be that it is slow – no longer.

We can now use… pic.twitter.com/d4QSRU9a6u

— Jiquan Ngiam (@JiquanNgiam) 20 février 2024

@GroqInc at almost 500 tokens/sec makes repeated self-reflection usable in production, changing everything. A key technique with LLMs is to use self-reflection (Reflexion) to get the model to do better. The problem used to be that it is slow – no longer. We can now use

→ View original post on X — @jiquanngiam