tegwick d0e6438609 Integrate founding explorations and bootstrap operational radar

Assistant: codex
Assistant-Model: gpt-6-astra
Assistant-Session: 01a09c77-b1a9-7eb3-b501-6cb24b458c97

2026-09-13 22:42:09 +02:00

3.3 KiB

Raw Permalink Blame History

Founding integration review — 2026-09-13

Inputs and evaluation

Both source ZIPs remain unchanged in history/; history/MANIFEST.json records SHA-256 checksums. ChatGPT contributes 13 files and Grok contributes 17 files (including a DOCX charter and its JavaScript generator). Neither is a runtime. The DOCX and generator remain recoverable from the Grok archive; its Markdown content supplies the working charter without introducing a document-build dependency. The archive READMEs and ChatGPT MANIFEST remain in the ZIPs as provenance.

ChatGPT is stronger on entity boundaries, historical reproducibility, source discipline, benchmark validity, task-specific ranking, cost accounting, and calibration. Its architecture is aspirational and its catalogs lack versioned observed results. Grok is stronger on accessible theory maps, editorial cadence, a practical watchlist, and a usable ticket shape. Its illustrative routing arithmetic overstates confidence. Both include dated factual claims without captured retrieval evidence; neither can seed a trusted production model/price database without verification.

Resolution

Conflict or gap	Integrated decision
Two descriptions and methods	INTENT governs; TaskModelEvaluationMethod and policies govern the advisor; task-router is the operator interface
Fixed Grok weights vs task-specific selection	Select five distinct instruments using benchmark-selection-v0.1; normalize task-specific weights and report weak coverage
Benchmark percent equals P(success)	Preserve task-fit proxy separately; no Sufficient/Budget claim without adequate calibration evidence
Grok 0.70/0.85 vs ChatGPT risk thresholds	Adopt exploratory .60, routine .80, important .90, high_assurance .97 as explicit provisional policies
Less than 10% vs inclusive 0.90 formula	Adopt at most 10% degradation (inclusive .90 boundary)
Price conflicts, e.g. Terra ranges; blended vs separate rates	Retain historical drafts, do not choose an unsupported price; require dated deployment-specific evidence
Fixed p25/p50/p75 vs p50/p90	Use p50/p90 where justified; otherwise a labeled assumption range, never fabricated quantiles
Aggregate index in worked example	Supersede operational example; retain original in ZIP; composite index cannot replace one of the five instruments
External automation IDs described as live	Archive-only references; scheduling here is planned and disabled
PostgreSQL/object storage target with no implementation	Start with auditable Git + content-addressed JSON; retain migration as future work

Imported file treatment

ChatGPT root design files, policy YAML, benchmark seed and landscape were promoted. Grok compendium, watchlist, frontier snapshots and dated digests were imported with unverified-draft banners. Router method/template/example and ops instructions were rewritten to agree with the governing method. The atlas remains candidate discovery, not a source of verified benchmark versions. Raw originals remain in the ZIPs.

Acceptance evidence

make check checks archive integrity, core files, and the observation ledger and runs behavior tests. make demo exercises record → validate → daily/weekly draft without polluting the operational ledger. Statehub results are recorded in docs/evidence/bootstrap.md after synchronization.

3.3 KiB Raw Permalink Blame History