Category: LLM Infrastructure
-
Self-Scaffolding LLMs: How Ornith-1.0 Rewrites Its Own Harness Mid-Training
A technical breakdown of DeepReinforce’s self-improving agentic coding models There’s a quiet assumption baked into most RL post-training pipelines for coding agents: a human designs the harness, and the model just gets better at using it. The scaffold — memory management, error handling, tool orchestration, retry logic — stays fixed. The policy is the…
-
Why a 7B Parameter Model Won’t Run Comfortably on a 14 GB GPU (And Why Most Engineers Get This Wrong)
If you’ve recently started working with Large Language Models (LLMs), you’ve probably seen a calculation like this: 7 Billion Parameters × 2 Bytes (FP16) ≈ 14 GB At first glance, it seems perfectly reasonable to conclude: “A GPU with 14 GB of VRAM should be enough.” Unfortunately, that’s one of the most…