Model Routing / Agent SystemsGPT-6 Sol vs Luna routing for agents
GPT-6 Sol vs. Luna vs. Astra: a routing policy for coding agents — and when local still wins
A routing policy for the actual GPT-6 lineup: Sol for discovery and coding, Luna for bounded high-volume processing, Astra when nothing else holds — each with a verification contract, and the lanes where a local 27B still beats all three.
Benchmarks / Agentssmall model benchmark video editing MCP guardrails
The Equalizer Bench: a 3B that can't write ffmpeg, the same 3B shipping video edits, and the bug our own benchmark caught
We benchmarked our own thesis: tiny model + deterministic guardrail layer vs raw capability. The curve is textbook, the trim trap is real, and the bench indicted our own product before anyone else could.
Local LLM / Servingspeculative decoding llama.cpp draft model iGPU speedup
The One-Line Bug That Crashed Our Fast Lane: finding, fixing, and measuring a speculative-decoding crash on a $1,400 mini-PC
Spec decoding crashed our fastest lane on day one. The bug was one missing line in our fork; the fix bought +17.7% and a surprise about draft quantization.