Stories by teugent

Most LLM cost isn't compute – it's identity drift (110-cycle GPT-4o benchmark)

Show HN: Sigma Runtime ERI (v0.1) – Open benchmark for attractor-based LLMs

Show HN: Sigma Runtime ERI – 800-line open cognitive runtime for LLM continuity

Show HN: Sigma Runtime – A Cognitive Runtime Standard for LLMs