Matt Pocock: Agents Are Good at Strategic Programming, They Just Aren't Trained to Care
mattpocockuk · x · 2026-10-08
Matt Pocock argues that AI agents are actually good at strategic programming, but they aren't RL-trained to care about anything beyond the task at hand. His fix: explicitly instruct your agent to care about the codebase. He adds that the deeper issue is human — most people don't care about codebase health as long as the code works, and that mindset needs to change.
More from coding & agent
- 30 个真实业务工作流清单：别把 Agent 测试搞复杂了 — VibeMarketer_ · 2026-10-08
- Hybrid agent pattern: cloud Gemini plans, local Gemma swarm runs 97% of tokens offline — clmt · 2026-10-08
- Agent compaction drift: limits cascade into agents policing cgroups instead of doing the work — generativist · 2026-10-08
- Long-running agents suffer 'constraint amplification': a subtle form of context rot — generativist · 2026-10-08
- Nautilo Ships Text+Vision Model Split, Preps Price/Security-Based Model Routing Gateway — Dan_Jeffries1 · 2026-10-08
- A fine-tuned 9B beats a 31B model: 600 labels, $0.12, 91% accuracy — julsimon · 2026-10-08