Agent unit tests are simplistic — the hard part was always realistic integration testing
srchvrs · x · 2026-09-28
In a follow-up to his thread on coding agents' intent drift, srchvrs argues the hard part of testing was never unit tests: it's realistic integration testing in nondeterministic environments you don't fully understand. Agent-generated unit tests are indeed simplistic, but they only cover the easy half of the problem.
More from coding & agent
- Liquid AI makes the case for edge agents: 350M-2.6B models with no per-token bill — JosephJacks_ · 2026-09-28
- X's invite-only bot creator program raises calls for agent usage dashboards — RachelVT42 · 2026-09-28
- A prompt trick to make quota-limited coding agents resume after interruptions — umeshonai · 2026-09-28
- Dev runs Bonsai 2 locally on Mac Studio to diff medication lists in 5.75 seconds — MaziyarPanahi · 2026-09-28
- Fixing Claude Opus 5.5 long-context drift with an external SESSION_STATE.md protocol — dr_cintas · 2026-09-28
- Data labeling firm sees Fortune 1000 revenue shift and evals as core enterprise IP — Scobleizer · 2026-09-28