Topic
Birgitta B Ckeler
3 episodes
-
Viability of local models for coding
Birgitta Böckeler tests local LLM viability for coding after a year away from the space. She maps a complex web of factors—RAM, model size, quantization, tool calling, context windows, reasoning modes—that determine whether small models actually work for agentic coding on consumer hardware (M3 Max / M5 Pro). Her core finding: locals are runneable and faster than a year ago, but tool calling is still shaky, reasoning can backfire, and quality is hit-or-miss. She's not claiming local models are ready to replace cloud APIs; she's charting what actually works and what doesn't on real machines.
-
Harness engineering for coding agent users
Vince and Ava discuss Birgitta Böckeler's Martin Fowler article on harness engineering for coding agents — the feedforward/feedback model, computational vs inferential controls, and why the behaviour harness category remains unsolved.
-
Harness engineering for coding agent users
Justy and Cody dig into harness engineering for coding agents: the practical idea that trust in AI-written code comes less from the model itself and more from the guardrails, checks, and feedback loops wrapped around it. They unpack feedforward guides versus feedback sensors, deterministic tooling versus LLM-based judgment, and why teams should treat the human as the person tuning the harness instead of reviewing every tiny diff forever.