zeeg on taming agent test spam: keep only integration tests, add caches and memory
zeeg · x · 2026-10-09
- Responding to jamwt's quip that "confident humans use more compute, tests make humans feel confident, tests generate tokens," zeeg shares his own agent testing practices.
- After plenty of forced test refactoring, he dropped most tests that aren't true integration tests, added deterministic caches and helpers to limit errors, and used skills/memory to dedupe and enforce policies.
More from coding & agent
- Temporal runs the Pi coding agent on durable execution to survive machine failures — francesc · 2026-10-09
- Zed CEO Nathan Soller: AI-generated unit tests are slop, integration tests are the right middle ground — zeeg · 2026-10-09
- Jev pitched as the fastest AI model for agents: millisecond decisions at near-zero cost — Arindam_1729 · 2026-10-09
- Devs debate whether LLMs should write tests: 'tests expose things memory can't hold' — ivan_bezdomny · 2026-10-09
- Musk shows Grok agent setting up 16 emulators on a handheld with one prompt — elonmusk · 2026-10-09
- MCPtoAI: open-source client shares MCP tools across AI models while credentials stay on-device — abktya · 2026-10-09