Register and share your invite link to earn from video plays and referrals.

Tomas Hernando Kofman
@tomas_hk
building ¬◇, intelligent model routing for coding agents
Joined April 2012
798 Following    3.5K Followers
Across various tasks and models, Val shows that an oracle router would beat the best single model by 14 points while costing about 40% less. But understanding how to evaluate router performance is much harder in production. We shared our work at @notdiamond_ai on using simulated users to evaluate coding agent routing, accounting for long sessions, user interactions, and cache dynamics that impact real-world costs and performance. Check it out:
Show more
Models are shipping faster than ever. In this past month alone, Vals tested 16 new LLMs and no single model leads on everything. That is why routers have become a core primitive in the AI stack. We partnered with @OpenRouter, @tryramp, @FireworksAI_HQ and @notdiamond_ai to share what’s missing in how routers get evaluated. Check out our latest blog:
Show more