// Field notes
Notes from the lab.
Short write-ups on what I learn building agent systems.
- Approval gates are a feature, not friction Why my agent harnesses pause for a human at the right moments, and how to do it without becoming the bottleneck. #harness#safety#claude-code
- The model never picks the number Using an LLM as a judge works only when the judge collects evidence and something deterministic does the scoring. #evals#llm-as-judge
- When Nemotron thinks it's Qwen I asked a 4B NVIDIA model "tell me about yourself", and it confidently introduced itself as a different company's model. #local-llms#identity#evals