Tomas Hernando Kofman

@tomas_hk

building ¬◇, intelligent model routing for coding agents

notdiamond.ai

Joined April 2012

Pinned
Tomas Hernando Kofman
@tomas_hk
Aug 4
Today we’re announcing Not Diamond Code, the world’s most powerful intelligent model router for long-horizon coding agents. Not Diamond works with any gateway or harness, including Claude Code, to select the best model and reasoning effort for each step, reducing costs by 20-65%
00:00
Tomas Hernando Kofman
@tomas_hk
Aug 10
Great article from Fortune on routing's challenges, Not Diamond, and why every company is trying to set up intelligent model routing now. We've been working on this problem since 2023 and there are a *lot* of dead ends where routing will cost you *more* money. This quote from
Why every company wants an AI model router right now | Fortune
From fortune.com
Tomas Hernando Kofman
@tomas_hk
Aug 7
This new Nvidia paper is huge for model routing and the future of inference: re-using the KV cache across different LLMs. One of the greatest challenge in model routing during long-horizon agent settings is that the cache does not transfer across different models. As a result,
Tomas Hernando Kofman
@tomas_hk
Aug 6
I'm giving a talk on model routing today at #Ai42026. If managing AI inference spend is a priority for your organization, please drop by! I'll also be available after the talk for Q&A. @Ai4Conferences
Tomas Hernando Kofman
@tomas_hk
Jul 31
Claude Code is the hegemony. Across the enterprises we work with, we see Claude Code dominating 80% of usage and spending. *But* I think this position is tenuous: - Enterprises often lag the frontier by 6 months. Claude Code's big moment was 6 months ago, so we'll see peak