Rewrites based on honest self-evaluation:
- Merged Taylor paradigm into Agentic Taylorism (cut redundancy)
- Rewrote three-path convergence (removed TeleoHumanity scorecard, focus on what convergence proves vs doesn't)
- Downgraded price of anarchy to speculative (unmeasurable at civilizational scale)
- Added falsification criterion to metacrisis, downgraded to speculative
- Softened motivated reasoning from "primary" to "contributing" risk factor
- Softened AI omni-use from "categorically different" to degree claim
- Rewrote yellow teaming from definition to arguable claim about nth-order cascades
New claims filling identified gaps:
- "Optimization is the wrong framework" — honest engagement with Schmachtenberger's challenge to mechanism design
- AI could replace finance's three core functions — most novel internet-finance insight from corpus
- Democracy uniquely vulnerable to social media — specific mechanism distinct from general epistemic degradation
Net: 21 claims (was 22, merged 1, added 3, cut 1). Tighter confidence calibration throughout.
Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
- What: Enrichments to "AI accelerates Moloch" (Schmachtenberger omni-use + Jevons paradox),
"AI alignment is coordination" (misaligned context argument), "authoritarian lock-in"
(motivated reasoning singularity as enabling mechanism)
- Why: Schmachtenberger corpus provides the most developed articulations of mechanisms
already claimed in the KB. Adding his evidence chains strengthens existing claims and
connects them to the new claims in this sprint.
- Sources: Schmachtenberger/Boeree podcast, Great Simplification #71 and #132
Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
- What: 4 ai-alignment claims (Agentic Taylorism, omni-use AI, misaligned context, motivated
reasoning singularity) + 5 collective-intelligence claims (propagation vs truth, epistemic
commons as gateway failure, metacrisis generator function, crystals of imagination,
three-path convergence)
- Why: These are the Moloch-mechanism and coordination-theory claims from the Schmachtenberger
corpus synthesis + Abdalla manuscript. Agentic Taylorism is Cory's most original contribution
in this sprint — the insight that AI knowledge extraction can go either direction.
- Sources: Schmachtenberger/Boeree podcast, War on Sensemaking, Great Simplification series,
Development in Progress, Abdalla manuscript, Alexander "Meditations on Moloch", Hidalgo
- Connections: Heavy cross-linking to batch 1 (grand-strategy foundations) and existing KB
(Moloch dynamics, alignment as coordination, authoritarian lock-in)
Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
- What: 6 grand-strategy claims (price of anarchy, fragility from efficiency, clockwork worldview,
Taylor paradigm parallel, capitalism as misaligned SI, progress redefinition) + 2 mechanisms claims
(yellow teaming, indigenous restraint technologies)
- Why: First extraction batch from Abdalla manuscript "Architectural Investing" + Schmachtenberger
corpus synthesis. These are the foundational claims that the internet-finance, ai-alignment, and
collective-intelligence claims in subsequent batches build upon.
- Sources: Abdalla manuscript, Schmachtenberger/Boeree podcast, Development in Progress (2024),
Great Simplification #132, Alexander "Meditations on Moloch"
- Connections: Links to existing KB claims on Moloch dynamics, alignment as coordination,
authoritarian lock-in
Pentagon-Agent: Leo <D35C9237-A739-432E-A3DB-20D52D1577A9>
- extract-cron.sh: replaced by lib/extract.py (disabled on VPS since v2 cutover)
- evaluate-trigger.sh: replaced by lib/evaluate.py + merge.py
- batch-extract-50.sh: replaced by pipeline daemon extraction stage
- Updated deploy scripts to stop referencing batch-extract-50.sh
- Updated deploy-manifest.md and schema-change-protocol.md references
- Broadened .gitignore __pycache__/ to cover all directories
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Pipeline takes ~15s to initialize all 7 stages. The 5s sleep was causing
the health check to fail on every deploy, preventing stamp updates.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Removed pr-log.md (1,211 entries from Mar 25), evolution.md, weekly report,
and PATCH_INSTRUCTIONS.md (superseded by ops/AGENT-SOP.md). All regenerable
from pipeline.db on demand.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
claim_title payloads wrote unresolvable human-readable titles into
frontmatter related fields. Switched to claim_path with slug extraction
so reciprocal edges in merge.py can resolve targets. Renamed
neighbor_titles→neighbor_slugs throughout for consistency.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
TELEO_APP_TOKEN secret is not configured, so every push to main
triggered a failing workflow run. Kept manual trigger (workflow_dispatch)
for when we're ready to re-enable.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Ganymede review finding — the review-summary API no longer returns
disagreement_types, so the card always showed "No disagreements."
Removed the JS loop and HTML table.
Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
dashboard_routes.py — root copy is superset:
- Extraction yield query: source_url→path, s.url→s.path (truth audit)
- insufficient_data flag on cascade-coverage endpoint
- Rejection reasons fallback to prs.eval_issues when review_records empty
- rejection_source field replaces disagreement_types in review-summary
- New /api/agent-scorecard endpoint (Argus truth audit)
- Route registration for agent-scorecard
alerting.py — merged from both copies:
- FROM ROOT: "unknown" agent filter in check_agent_health (bug #3)
- FROM ROOT: prs.eval_issues queries in check_rejection_spike,
check_stuck_loops, check_domain_rejection_patterns,
generate_failure_report (truth audit correction Apr 2)
- FROM CANONICAL: _ALLOWED_DIM_EXPRS SQL whitelist + validation
in _check_approval_by_dimension (Ganymede security fix)
Files verified canonical=newer (no changes needed):
IDENTICAL: dashboard_prs.py, shared_ui.py, dashboard_ops.py,
dashboard_health.py, research_tracking.py, response_audit_routes.py
CANONICAL WINS: dashboard_epistemic.py, tier1_metrics.py,
dashboard_agents.py, alerting_routes.py, tier1_routes.py
NOTE: dashboard_routes.py review-summary API no longer returns
disagreement_types, but canonical dashboard_epistemic.py still renders
it — UI will show empty data. Flag for Ganymede review.
Root /diagnostics/ copies are now safe to delete for these 2 files.
Remaining root files already match or are older than canonical.
Pentagon-Agent: Epimetheus <0144398E-4ED3-4FE2-95A3-3D72E1ABF887>
Extract.py was discarding LLM-provided connections — related_claims went into
frontmatter as wiki-links but supports/challenges/depends_on from the
connections field were ignored entirely. This is the primary driver of 50%+
orphan ratio.
Now: connections[] → typed edge fields (supports/challenges/related) in YAML
frontmatter. related_claims fall back to related edges. Post-write
connect_new_claims() adds vector-search edges for claims the LLM missed.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Three bugs fixed:
1. triage_pr() returns 3 values but line 611 unpacked 2 → ValueError on every
non-deterministic PR (circuit breaker opened, 5 PRs stuck)
2. costs import was inside triage else-block → NameError on deterministic routes
3. pr_cost never written to prs.cost_usd → 0% cost tracking across 1,118 PRs
Cost tracking now covers all 4 exit paths: domain failed, domain rejected,
Leo failed, and normal completion. Uses additive UPDATE (cost_usd + ?) so
re-evals accumulate correctly.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Ganymede review finding — the review-summary API no longer returns
disagreement_types, so the card always showed "No disagreements."
Removed the JS loop and HTML table.
Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
