How do you stop GPT from generating junk unit tests all the time?
zeeg · x · 2026-07-29
The author asks for a testing policy, doc, or skill that can stop GPT from producing low-value unit tests.
Their preference is to focus on higher-level tests that cover multiple behaviors, with only a minimal number of unit tests. The problem is that GPT keeps generating junk unit tests despite repeated attempts to steer it away from them.
More from coding & agent
- AI coding agents may be killing the developer flow state — bendee983 · 2026-07-29
- StateAct hits a new OSWorld 2.0 SOTA by using program state instead of pixels — LiJunnan0409 · 2026-07-29
- Huawei’s SearchArt trains a 27B long-horizon search agent with verified synthetic tasks — _reachsumit · 2026-07-29
- Agent Retrieval Bench tests whether coding agents can find the right repo files before patching — _reachsumit · 2026-07-29
- TopoGR preserves semantic-ID topology for generative recommendation with Hamming geometry — _reachsumit · 2026-07-29
- Grevo turns semantic-ID assignment into an evolvable variable for generative recommendation — _reachsumit · 2026-07-29