Ornith-1.0: self-improving open-source models for agentic coding

AI Coding at Home Without Going Broke

Granite 4.1: IBM's 8B Model Matching 32B MoE

Kimi vendor verifier – verify accuracy of inference providers

LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?

Sarvam 105B, the first competitive Indian open source LLM