Tomas Hernando Kofman (@tomas

Tomas Hernando Kofman

769 posts

Tomas Hernando Kofman

@tomas_hk

building ¬◇, intelligent model routing for coding agents

Joined April 2012

Pinned
Tomas Hernando Kofman
@tomas_hk
Jun 8
My thoughts on the future of model routing and AI: - We have not even scratched the surface of runaway inference costs - Solving this requires intelligent model routing, especially as the inference landscape continues fragmenting. This is a *hard* problem. - Naive solutions
Matthew Berman
@MatthewBerman
Jun 8
I made an angel investment in @tomas_hk two years ago, believing model routing would become a massive business. Now companies are spending $500m per month on tokens. Increased quality and decreased cost are not mutually exclusive. Here's Tomas' essay about how Model Routing
Tomas Hernando Kofman
@tomas_hk
May 20, 2025
Today we’re launching Prompt Adaptation, a state-of-the-art agentic system that automatically adapts prompts across LLMs. Prompt Adaptation outperforms all other methods and significantly improves accuracy over manual prompt engineering, saving you thousands of hours per year.
00:00
Tomas Hernando Kofman
@tomas_hk
Dec 12, 2023
1/9 huggingface.co/notdiamond/not… We’re open-sourcing a lightweight preview of our router that sends queries to either GPT-3.5 or GPT-4, maximizing accuracy while drastically reducing costs and latency. Routing to Gemini, Mistral, Claude, and Llama coming soon. A few quick points:
notdiamond/notdiamond-0001 · Hugging Face
From huggingface.co
Tomas Hernando Kofman
@tomas_hk
Jul 30, 2024
Today we're releasing Not Diamond… The world’s most powerful AI model router. Not Diamond maximizes LLM output quality by automatically recommending the best LLM on every request at lower cost and latency. And it takes <5m to set up. Watch this to see how to start using it:
00:00
Tomas Hernando Kofman
@tomas_hk
Sep 24, 2024
Today we're open-sourcing RoRF (Routing on Random Forests), a pairwise model router that beats all closed and open-source approaches, along with 12 pre-trained model routers: Hugging Face: huggingface.co/notdiamond Github: github.com/Not-Diamond/Ro… Blog: notdiamond.ai/blog/rorf
notdiamond (Not Diamond)
From huggingface.co
Tomas Hernando Kofman
@tomas_hk
Aug 1, 2024
This is the last chatbot you’ll ever need. Yesterday, @mckaywrigley built an oss Not Diamond-powered chat app. We loved it. So today we’re releasing a hosted version. Get the best LLM on every message and hyper-personalize routing to your preferences with feedback. Watch how:
00:00
Tomas Hernando Kofman
@tomas_hk
Jun 21, 2024
Standing-room only @websim_ai hackathon last night—so happy we could do this and thanks to everyone for coming and hanging out. Some of the coolest highlights in thread:
Tomas Hernando Kofman
@tomas_hk
Feb 18, 2025
We're hiring engineers and researchers to build the future of multi-model AI infrastructure. We're a small, technically elite team backed by Jeff Dean, Julien Chaumond, Ion Stoica, + more. And we guarantee a $50K investment in your next startup for every year you work with us.
Not Diamond open roles
From notdiamond.notion.site
Tomas Hernando Kofman
@tomas_hk
Nov 12, 2024
You can now use Not Diamond in Raycast to get recommended the best LLM on every message you send. It's super simple to set up—and I love having this just a shortcut away. s/o to @raycastapp and @thomaspaulmann for building such an incredible interface 🩶Set up link below 👇
00:00
Tomas Hernando Kofman
@tomas_hk
Oct 22, 2024
New top rankings for models on over 500,000 samples of real-world human preference data: 1. Claude 2. Mistral(!) 3. Perplexity Claude 3.5 Sonnet is preferred by users over all other models. Surprisingly however, the next-best models are Mistral Large 2 and Perplexity(!),
Tomas Hernando Kofman
@tomas_hk
Aug 28, 2024
Since launching Not Diamond chat a few weeks ago, we've had over 100,000 messages sent with 37.6% of messages receiving feedback(‼️) First image: rankings across all models (sonnet > gpt-4o) Second image: my personal ranking (perplexity 💜) Reply to get your personal ranking.
Tomas Hernando Kofman
@tomas_hk
Jan 4, 2024
Hiring a founding engineer: tomashernandokofman.notion.site/Founding-Engin… Competitive salary, generous equity, robust benefits, and a guaranteed investment in a future startup if you ever decide to build something yourself down the line.
Tomas Hernando Kofman
@tomas_hk
Jul 30, 2024
Replying to @tomas_hk
Not Diamond sets new SOTA standards on major benchmarks like GPQA, Arena Hard, MMLU, and HumanEval. We achieve this by ensembling every other model into a meta-model that learns when to call each LLM. Routing opens a new frontier for the performance and generalizability of LLMs.
Tomas Hernando Kofman
@tomas_hk
Jan 9, 2025
You can now use Not Diamond in @openrouter! Access 293 top models with a single API key and automatically get routed to the best one for your use case. OpenRouter is one of the most important AI dev platforms out there. Excited to see what folks build! 🙌 @alexatallah
OpenRouter
@OpenRouter
Jan 7, 2025
Replying to @OpenRouter
5. New Auto Router Will post more details in the coming weeks, but you can get a sneak peak here: openrouter.ai/openrouter/auto 🧠 It now routes to 19 different models, optimizing for quality, powered by Not Diamond. 💬 The chatroom now more clearly shows which model was used. The