Teknium Claims Big Token Efficiency Gains in Hermes; User Reports 89% Savings vs Codex

Teknium · x · 2026-09-07

Nous Research's Teknium says Hermes made huge token efficiency improvements over the past two weeks, inviting users to try codex subagents in Hermes Agent. A quoted user reports the same workload that burned 2.5 Astra Medium resets in the ChatGPT Codex app in half a day used only 11% of quota all day with Hermes ULTRA and FAST modes — the first hard evidence of "less is far more" in Hermes.

Original post →

More from coding & agent

coding & agent channel →