0a8e77e949
- Moved everything from ideas/passepartout/ to projects/passepartout/ - Moved legal structures to projects/flags/ - Created missing _index.org files for all subdirectories - Stripped redundant passepartout- prefix from filenames - Rewrote root _index.org as generalized brain index (projects + concepts) - Updated Hugo nav to Projects/Concepts - Updated build script section descriptions - Deleted stale ideas/passepartout-economics.md orphan
1.6 KiB
Gate Rule Encoding from Codified Domains
Laws, regulations, standards, procedures, and technical specifications are already written down in structured text. The LLM does not need to reason about them — it needs to translate them into gate rules and ACL2 theorems.
Example: The US Federal Acquisition Regulation (FAR) is ~2,000 pages. A frontier LLM can ingest the FAR and produce a plist of gate rules:
- (if contract > $250K AND not small-business-set-aside → :deny)
- (if sole-source AND no justification-documented → :deny, produce-justification)
ACL2 verifies the rule set for internal consistency. Screamer checks against existing compliance facts. The human reviews the bootstrap output and approves or corrects individual rules.
The key distinction: the LLM is not extracting knowledge from prose — it is translating a known rule system into a formal representation. The result is not "the LLM's best guess" but "the rule set as stated in the source document, mechanically transcribed."
For codified domains, the encoding cost drops from weeks to hours. The only bottleneck is human review of the 5% ambiguous rules. This is what makes the sufficiency flip economically viable — once gates are encoded, verification is near-free. The resulting rules are packaged into domain gate packages that can be reused across deployments.