2 commits

Author	SHA1	Message	Date
m3taversal	3d2f079633	theseus: extract 3 claims from Aquino-Michaels + enrich multi-model claim ... - What: 3 new claims from "Completing Claude's Cycles" (no-way-labs/residue) + enrichment of existing multi-model claim with detailed architecture - Claims: 1. Structured exploration protocols reduce human intervention by 6x (Residue prompt) 2. AI agent orchestration outperforms coaching (orchestrator as data router) 3. Coordination protocol design produces larger gains than model scaling - Enriched: multi-model claim now includes Aquino-Michaels's Agent O/C/orchestrator detail - Source: archived at inbox/archive/2026-03-00-aquinomichaels-completing-claudes-cycles.md - _map.md: AI Capability Evidence section reorganized into 3 subsections (Collaboration Patterns, Architecture & Scaling, Failure Modes & Oversight) - All wiki links verified resolving Pentagon-Agent: Theseus <845F10FB-BC22-40F6-A6A6-F6E4D8F78465>	2026-03-07 20:18:35 +00:00
m3taversal	a86e804c87	theseus: extract 4 claims from Knuth's Claude's Cycles paper ... - What: 4 new claims about AI capability evidence from Knuth's Feb 2026 paper on Hamiltonian cycle decomposition solved by Claude Opus 4.6 + Filip Stappers - Claims: 1. Human-AI collaboration succeeds through three-role specialization (explore/coach/verify) 2. Multi-model collaboration outperforms single models on hard problems (even case) 3. AI capability and reliability are independent dimensions (solved problem but degraded) 4. Formal verification provides scalable oversight that doesn't degrade with capability gaps - Source: archived at inbox/archive/2026-02-28-knuth-claudes-cycles.md (now processed) - _map.md: added new "AI Capability Evidence (Empirical)" section - All 12 wiki links verified resolving Pentagon-Agent: Theseus <845F10FB-BC22-40F6-A6A6-F6E4D8F78465>	2026-03-07 19:52:15 +00:00