Show HN: Building a full agentic harness around a 4B model is hard

By mehrant · 2026-08-19 · 3 points · 0 comments

Around 3 months ago, we were thinking why none of the iPhone apps running an LLM are built as a full harness (as in inference + agentic loop + context management + tools + MCP servers and etc.). It became more interesting when we noticed even the new Siri is not fully on device…

Open the full discussion on BetterNews