
Dark factories: independent acceptance
Who checks the code nobody reads
Slide contents
1. Dark factories: independent acceptance
Who checks the code nobody reads
2. A verdict needs independent evidence
Contract, evaluator, test environment and future change
3. People define acceptable behavior
In the strict model, routine implementation review disappears
4. Self-checks can share a blind spot
One wrong assumption can enter both implementation and test
5. Workers cannot rewrite their final exam
Final scenarios live outside the worker’s write permissions
6. Hide probes; keep requirements public
Expected behavior is available before the run
7. Check exact outcomes exactly
Deterministic checks, model judges and experts answer different questions
8. Satisfaction concerns observed trajectories
Likely satisfactory outcomes depend on the scenario set
9. A twin makes failures reproducible
A behavioral API model provides controllable states
10. The simulator also creates blind spots
A useful external-service model has testable boundaries
11. The factory depends on its evaluation system
Specification, agent, scenarios and environment form a loop
12. Attractor publishes implementation specifications
NLSpecs: orchestrator, agent loop and unified client
13. The validator returns defects to workers
Factory Missions separates execution, validation and orchestration
14. Validation consumes substantial work
Published Slack-like project: 16.5 hours in total
15. A repeated request exposes an extra effect
T1: one identifier, repeated delivery, one promised effect
16. Reports return evidence, not a ready fix
Observation, expectation, revision and reproduction guide repair
17. Current correctness does not guarantee evolvability
Read the lights-off account with its date and context
18. The next task tests inherited code
T4 starts from that system’s accepted T2 result
19. A coverage map beats one green status
Automatic checks, expert judgment and untested properties
20. Trust grows around verification boundaries
Contract, independent verdict, controlled environment and the next change