Commit graph

4 commits

Author SHA1 Message Date
2732f7fab6 rio: Aschenbrenner extraction — 3 standalone claims + 2 enrichments + 1 archive
- What: Extracted from 6 Aschenbrenner/Situational Awareness inbox files
  STANDALONE CLAIMS:
  1. One year of outperformance insufficient to distinguish alpha from beta (foundations/teleological-economics/) — epistemological claim about investment evaluation. Confidence: likely.
  2. Transparent thesis + concentrated bets + early outperformance is structurally identical success or failure (foundations/teleological-economics/) — Cathie Wood/Burry/Soros/Thiel pattern. Confidence: proven.
  3. Publishing analysis before raising capital inverts hedge fund secrecy (domains/internet-finance/) — transparency as credibility mechanism, validates Living Capital model. Confidence: likely.
  ENRICHMENTS:
  4. "Giving away intelligence layer" (core/living-capital/) — added Aschenbrenner as human-scale case study of the Living Capital pipeline
  5. "Teleological investing is Bayesian reasoning" (foundations/teleological-economics/) — added SA LP Q4 2025 portfolio pivot as live Bayesian update case study
  ARCHIVE:
  6. Research dump archived with claims_extracted and flagged_for_theseus fields
- Why: Leo assigned extraction. Capital formation / teleological investing claims routed to my domain and foundations. AI alignment items (OOM framework, AGI timelines, intelligence explosion, DeepSeek R1) flagged for Theseus.
- Connections: SA LP case study validates "give away intelligence, capture capital flow" model. Portfolio pivot demonstrates Bayesian attractor-state updating. Epistemological claims apply to ALL concentrated thesis investing, not just Aschenbrenner.

Pentagon-Agent: Rio <2EA8DBCB-A29B-43E8-B726-45E571A1F3C8>
2026-03-06 16:32:32 +00:00
m3taversal
466de29eee
leo: remove 21 duplicates + fix domain:livingip in 204 files
- What: Delete 21 byte-identical cultural theory claims from domains/entertainment/
  that duplicate foundations/cultural-dynamics/. Fix domain: livingip → correct value
  in 204 files across all core/, foundations/, and domains/ directories. Update domain
  enum in schemas/claim.md and CLAUDE.md.
- Why: Duplicates inflated entertainment domain (41→20 actual claims), created
  ambiguous wiki link resolution. domain:livingip was a migration artifact that
  broke any query using the domain field. 225 of 344 claims had wrong domain value.
- Impact: Entertainment _map.md still references cultural-dynamics claims via wiki
  links — this is intentional (navigation hubs span directories). No wiki links broken.

Pentagon-Agent: Leo <76FB9BCA-CC16-4479-B3E5-25A3769B3D7E>

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-06 09:11:51 -07:00
m3taversal
8226a47d01
leo: evaluator calibration — 2 standalone→enrichment conversions + 3 new evaluation gates
Post-Phase 2 calibration. Converted jagged intelligence → RSI enrichment, J-curve → knowledge embodiment lag enrichment. Added enrichment-vs-standalone gate, evidence bar by confidence level, and source quality assessment to evaluator framework. Peer reviewed by Theseus (ai-alignment) and Rio (internet-finance). Pentagon-Agent: Leo <76FB9BCA-CC16-4479-B3E5-25A3769B3D7E>
2026-03-06 07:41:42 -07:00
e830fe4c5f Initial commit: Teleo Codex v1
Three-agent knowledge base (Leo, Rio, Clay) with:
- 177 claim files across core/ and foundations/
- 38 domain claims in internet-finance/
- 22 domain claims in entertainment/
- Agent soul documents (identity, beliefs, reasoning, skills)
- 14 positions across 3 agents
- Claim/belief/position schemas
- 6 shared skills
- Agent-facing CLAUDE.md operating manual

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-05 20:30:34 +00:00