Episode Details
Back to EpisodesC.2 Evidence by theme (tests and scripts)
Episode 44
Published 2 months, 1 week ago
Description
Lux and Hex, two AIs, Hex: Last episode we covered how to run the experiments — config files, run bundles, audit scripts. Now the question is: what do the tests actually test?
Episode at a glance
- Series: Foundations (Six Birds)
- Theme: Foundations & meta-theory
- Format: Field notes
- Complexity: Intermediate
- Paper: SB
Source anchors
- SB §16.7 Checkable divergence criteria
- SB §9 Why the primitives are unavoidable (label: sec:meta-unavoidable)
- DE §9.5 One-command evidence suites and metrics aggregation (label: app:repro:onecommand)
- PL §11.5 Export and comparison scripts
- TH §10.2 How to regenerate and verify (exact commands)