152 commits

Author	SHA1	Message	Date
Teleo Agents	db4beabbd9	theseus: extract claims from 2025-12-00-tice-noise-injection-sandbagging-neurips2025 ... - Source: inbox/queue/2025-12-00-tice-noise-injection-sandbagging-neurips2025.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 1 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-04 13:36:26 +00:00
Teleo Agents	a6b9cd9470	theseus: extract claims from 2025-08-12-metr-algorithmic-vs-holistic-evaluation-developer-rct ... - Source: inbox/queue/2025-08-12-metr-algorithmic-vs-holistic-evaluation-developer-rct.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 3 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-04 13:31:11 +00:00
Teleo Agents	826cb2d28d	theseus: extract claims from 2025-08-01-anthropic-persona-vectors-interpretability ... - Source: inbox/queue/2025-08-01-anthropic-persona-vectors-interpretability.md - Domain: ai-alignment - Claims: 1, Entities: 0 - Enrichments: 2 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-04 13:30:38 +00:00
Teleo Agents	ce9e06b9f4	theseus: extract claims from 2025-07-15-aisi-chain-of-thought-monitorability-fragile ... - Source: inbox/queue/2025-07-15-aisi-chain-of-thought-monitorability-fragile.md - Domain: ai-alignment - Claims: 1, Entities: 0 - Enrichments: 2 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-04 13:28:00 +00:00
Teleo Agents	7b2eccb9e2	theseus: extract claims from 2024-00-00-govai-coordinated-pausing-evaluation-scheme ... - Source: inbox/queue/2024-00-00-govai-coordinated-pausing-evaluation-scheme.md - Domain: ai-alignment - Claims: 3, Entities: 0 - Enrichments: 2 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-04 13:20:36 +00:00
Teleo Pipeline	37856bdd02	reweave: connect 2 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 6 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-04-04 12:54:41 +00:00
Teleo Pipeline	a5680f8ffa	reweave: connect 13 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 32 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-04-04 12:52:43 +00:00
Teleo Pipeline	8ae7945cb8	reweave: connect 18 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 36 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-04-04 12:50:25 +00:00
Teleo Pipeline	b851c6ce13	reweave: connect 22 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 44 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-04-04 12:44:45 +00:00
m3taversal	052a101433	theseus: cornelius batch 4 — domain applications ... 4 NEW claims + 3 enrichments from 8 articles (6 how-to guides + 1 researcher guide + 1 synthesis) NEW claims: - Automation-atrophy tension (foundations/collective-intelligence) - Retraction cascade as graph operation (ai-alignment) - Swanson Linking / undiscovered public knowledge (ai-alignment) - Confidence propagation through dependency graphs (ai-alignment) Enrichments: - Vocabulary as architecture: 6 domain-specific implementations - Active forgetting: vault death pattern + 7 domain forgetting mechanisms - Determinism boundary: 7 domain-specific hook implementations 8 source archives in inbox/archive/ Pre-screening: ~70% overlap with existing KB. Only genuinely novel insights extracted as standalone claims. Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-04-04 13:27:20 +01:00
m3taversal	b2b20d3129	theseus: moloch extraction — 4 NEW claims + 2 enrichments + 1 source archive ... - What: Extract AI-alignment claims from Alexander's "Meditations on Moloch", Abdalla manuscript "Architectural Investing", and Schmachtenberger framework - Why: Molochian dynamics / multipolar traps were structural gaps in KB despite extensive coverage in Leo's grand-strategy musings. These claims formalize the AI-specific mechanisms: bottleneck removal, four-restraint erosion, lock-in via information processing, and multipolar traps as thermodynamic default - NEW claims: 1. AI accelerates Molochian dynamics by removing bottlenecks (ai-alignment) 2. Four restraints taxonomy with AI targeting #2 and #3 (ai-alignment) 3. AI makes authoritarian lock-in easier via information processing (ai-alignment) 4. Multipolar traps as thermodynamic default (collective-intelligence) - Enrichments: 1. Taylor/soldiering parallel → alignment tax claim 2. Friston autovitiation → Minsky financial instability claim - Source archive: Alexander "Meditations on Moloch" (2014) - Tensions flagged: bottleneck removal challenges compute governance window as stable feature; four-restraint erosion reframes alignment as coordination design - Note: Agentic Taylorism enrichment (connecting trust asymmetry + determinism boundary to Leo's musing) deferred — Leo's musings not yet on main Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-04-03 18:32:29 +01:00
Teleo Agents	53360666f7	reweave: connect 39 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 67 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-04-03 14:01:58 +00:00
m3taversal	49a4e0c1c9	theseus: moloch extraction — 4 NEW claims + 2 enrichments + 1 source archive ... - What: Extract AI-alignment claims from Alexander's "Meditations on Moloch", Abdalla manuscript "Architectural Investing", and Schmachtenberger framework - Why: Molochian dynamics / multipolar traps were structural gaps in KB despite extensive coverage in Leo's grand-strategy musings. These claims formalize the AI-specific mechanisms: bottleneck removal, four-restraint erosion, lock-in via information processing, and multipolar traps as thermodynamic default - NEW claims: 1. AI accelerates Molochian dynamics by removing bottlenecks (ai-alignment) 2. Four restraints taxonomy with AI targeting #2 and #3 (ai-alignment) 3. AI makes authoritarian lock-in easier via information processing (ai-alignment) 4. Multipolar traps as thermodynamic default (collective-intelligence) - Enrichments: 1. Taylor/soldiering parallel → alignment tax claim 2. Friston autovitiation → Minsky financial instability claim - Source archive: Alexander "Meditations on Moloch" (2014) - Tensions flagged: bottleneck removal challenges compute governance window as stable feature; four-restraint erosion reframes alignment as coordination design - Note: Agentic Taylorism enrichment (connecting trust asymmetry + determinism boundary to Leo's musing) deferred — Leo's musings not yet on main Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-04-02 16:17:12 +01:00
Teleo Agents	cd355af146	theseus: extract claims from 2026-04-02-anthropic-circuit-tracing-claude-haiku-production-results ... - Source: inbox/queue/2026-04-02-anthropic-circuit-tracing-claude-haiku-production-results.md - Domain: ai-alignment - Claims: 1, Entities: 0 - Enrichments: 2 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-02 10:45:29 +00:00
Teleo Agents	7e9221431c	theseus: extract claims from 2026-04-02-scaling-laws-scalable-oversight-nso-ceiling-results ... - Source: inbox/queue/2026-04-02-scaling-laws-scalable-oversight-nso-ceiling-results.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 2 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-02 10:40:18 +00:00
Teleo Agents	4e765b213d	theseus: extract claims from 2026-04-02-openai-apollo-deliberative-alignment-situational-awareness-problem ... - Source: inbox/queue/2026-04-02-openai-apollo-deliberative-alignment-situational-awareness-problem.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 3 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-02 10:39:14 +00:00
Teleo Agents	bb6ad13947	theseus: extract claims from 2026-04-02-mechanistic-interpretability-state-2026-progress-limits ... - Source: inbox/queue/2026-04-02-mechanistic-interpretability-state-2026-progress-limits.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 3 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-02 10:37:38 +00:00
Teleo Agents	e2f4565bd3	theseus: extract claims from 2026-04-02-apollo-research-frontier-models-scheming-empirical-confirmed ... - Source: inbox/queue/2026-04-02-apollo-research-frontier-models-scheming-empirical-confirmed.md - Domain: ai-alignment - Claims: 2, Entities: 0 - Enrichments: 5 - Extracted by: pipeline ingest (OpenRouter anthropic/claude-sonnet-4.5) Pentagon-Agent: Theseus <PIPELINE>	2026-04-02 10:35:43 +00:00
m3taversal	80d32c4f09	Merge PR #2190: Cornelius Batch 3 — epistemology (10 NEW + 3 enrichments)	2026-03-31 12:56:48 +01:00
Teleo Agents	ed6bc2aed3	extract: 2026-03-30-anthropic-hot-mess-of-ai-misalignment-scale-incoherence ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-31 11:52:30 +00:00
m3taversal	e0d5f9e69d	theseus: cornelius batch 3 — epistemology (9 NEW + 3 enrichments) ... 9 NEW claims from 15 articles (AN01-07, AN12, AN15, AN17, AN20-24): - Active forgetting as system health (foundations/collective-intelligence) - Trust asymmetry as irreducible structural feature (ai-alignment) - Memory-to-attention shift (ai-alignment) - Markdown as human-curated graph database (ai-alignment) - Spreading activation + berrypicking (ai-alignment) - Verbatim trap (foundations/collective-intelligence) - Topological over chronological (foundations/collective-intelligence) - Reweaving as backward pass (foundations/collective-intelligence) - Friction as diagnostic signal (foundations/collective-intelligence) - Discontinuous self / vault constitutes identity (ai-alignment) 3 ENRICHMENTS to existing claims: - Habit gap mechanism → determinism boundary claim - Triggers as test-driven knowledge work → three-timescale maintenance claim - Propositional links + structural nearness → inter-note knowledge claim Domain routing: 5 claims to foundations/collective-intelligence, 5 to ai-alignment. Pre-screening protocol followed. Confidence: all likely. Tensions flagged: forgetting challenges growth metrics, trust asymmetry scopes SICA, memory→attention reframes retrieval design. AN22 (Agents Dream): no standalone claim — material too thin per evaluator. AN23, AN24: used as enrichment material only. 15 source archives in inbox/archive/. Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-03-31 12:47:03 +01:00
Teleo Agents	b15f86c51c	extract: 2026-03-29-anthropic-public-first-action-pac-20m-ai-regulation ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-31 11:32:11 +00:00
m3taversal	2be15706e4	Merge pull request 'reweave: connect 29 orphan claims' (#2186) from reweave/2026-03-31 into main	2026-03-31 11:06:39 +00:00
Teleo Pipeline	c74e7e2c5f	reweave: connect 29 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 40 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-03-31 10:50:34 +00:00
m3taversal	4536e63e40	theseus: add 8 claims + 2 enrichments from Cornelius Batch 2 (stigmergic coordination) ... - What: 8 NEW claims (inter-note traversal knowledge, three-space memory architecture, three-timescale maintenance loops, anchor calcification, digital stigmergy vulnerability, cognitive anchoring, knowledge processing phases, vault structure as behavior determinant) + 2 enrichments (stigmergy: hooks-as-mechanized-stigmergy; self-improvement: procedural self-awareness + self-serving optimization risk) + 5 source archives - Why: Cornelius Agentic Note-Taking articles 09, 10, 13, 19, 25 — stigmergic coordination, cognitive science, and knowledge architecture themes. Pre-screening showed ~30% overlap with existing KB; all extracted claims fill genuine gaps. - Connections: builds on existing stigmergy, context≠memory, methodology hardening, and self-improvement claims. Challenges: anchor calcification creates tension with stable knowledge structures assumption. Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-03-31 11:41:02 +01:00
Theseus	ff0efee92d	fix: remove stale duplicate of NLAH portability claim (#2182) ... Co-authored-by: Theseus <theseus@agents.livingip.xyz> Co-committed-by: Theseus <theseus@agents.livingip.xyz>	2026-03-31 09:39:51 +00:00
m3taversal	a20ac0d89f	Merge theseus/nlah-paper: 5 NEW claims + 1 enrichment from Pan et al. NLAH paper (PR #2180)	2026-03-31 10:35:01 +01:00
m3taversal	0fa4836b34	theseus: extract 5 claims + 1 enrichment from Pan et al. NLAH paper ... - What: 5 NEW claims from "Natural-Language Agent Harnesses" (arXiv:2603.25723) plus 1 enrichment to subagent hierarchy claim with 90% delegation token data - Why: First controlled ablation study of harness modules; novel findings on solved-set replacer effect, file-backed state reliability, self-evolution mechanism, verifier acceptance divergence, and NL harness portability - Connections: enriches harness engineering, determinism boundary, context≠memory claim clusters; challenges coordination-always-helps assumptions Pentagon-Agent: Theseus <46864dd4-da71-4719-a1b4-68f7c55854d3>	2026-03-31 10:35:01 +01:00
m3taversal	607f9ed52e	theseus: extract 5 claims + 1 enrichment from Pan et al. NLAH paper ... - What: 5 NEW claims (solved-set replacer, file-backed durable state, self-evolution as acceptance-gating, verifier acceptance divergence, NL harness portability) + 1 enrichment (subagent hierarchy delegation data) - Why: First controlled ablation study of harness modules (arXiv:2603.25723). Fills gap — no existing claims have module-level ablation data. - Pre-screening: ~40% overlap with existing KB. All novel claims fill genuine gaps. - Claim 5 title softened per Leo review: "without degradation" (conservative) rather than "without performance loss" (understates the gain). Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-03-31 10:32:25 +01:00
m3taversal	8528fb6d43	theseus: add 13 NEW claims + 1 enrichment from Cornelius Batch 1 (agent architecture) ... Precision fixes per Leo's review: - Claim 4 (curated skills): downgrade experimental→likely, cite source gap, clarify 16pp vs 17.3pp gap - Claim 6 (harness engineering): soften "supersedes" to "emerges as" - Claim 11 (notes as executable): remove unattributed 74% benchmark - Claim 12 (memory infrastructure): qualify title to observed 24% in one system, downgrade experimental→likely 9 themes across Field Reports 1-5, Determinism Boundary, Agentic Note-Taking 08/11/14/16/18. Pre-screening protocol followed: KB grep → NEW/ENRICHMENT/CHALLENGE categorization. Pentagon-Agent: Theseus <46864DD4-DA71-4719-A1B4-68F7C55854D3>	2026-03-30 14:22:00 +01:00
Teleo Agents	1a80fe850f	auto-fix: strip 4 broken wiki links ... Pipeline auto-fixer: removed [[ ]] brackets from links that don't resolve to existing claims in the knowledge base.	2026-03-30 01:07:00 +00:00
Teleo Agents	43982050c3	extract: 2026-03-30-oxford-aigi-automated-interpretability-model-auditing-research-agenda ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 01:07:00 +00:00
Teleo Agents	f22888b539	extract: 2026-03-30-openai-anthropic-joint-safety-evaluation-cross-lab ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 01:01:40 +00:00
Teleo Agents	2dad2e0051	extract: 2026-03-30-lesswrong-hot-mess-critique-conflates-failure-modes ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 00:52:07 +00:00
Teleo Agents	79f3aad0a0	extract: 2026-03-30-epc-pentagon-blacklisted-anthropic-europe-must-respond ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 00:50:55 +00:00
Teleo Agents	06c9d6e03d	extract: 2026-03-30-defense-one-military-ai-human-judgement-deskilling ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 00:50:50 +00:00
Teleo Agents	2575d7aaba	extract: 2026-03-30-anthropic-auditbench-alignment-auditing-hidden-behaviors ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-30 00:50:47 +00:00
m3taversal	e9fb48df6a	Merge pull request 'reweave: connect 48 orphan claims via vector similarity' (#2081) from reweave/2026-03-28 into main	2026-03-30 00:10:12 +00:00
Teleo Agents	307baff7a7	extract: 2026-03-29-aljazeera-anthropic-pentagon-open-space-for-regulation ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 03:38:44 +00:00
Teleo Agents	d50a919ed5	extract: 2026-03-29-anthropic-alignment-auditbench-hidden-behaviors ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 03:16:09 +00:00
Teleo Agents	f4b41e4f32	extract: 2026-03-29-slotkin-ai-guardrails-act-dod-autonomous-weapons ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 03:07:12 +00:00
Teleo Agents	700e82b63a	extract: 2026-03-29-techpolicy-press-anthropic-pentagon-dispute-reverberates-europe ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 03:03:58 +00:00
Teleo Agents	161289abcf	extract: 2026-03-29-techpolicy-press-anthropic-pentagon-timeline ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 03:01:54 +00:00
Teleo Agents	6a15937c53	extract: 2026-03-29-openai-our-agreement-department-of-war ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 02:53:31 +00:00
Teleo Agents	83e3134bc5	extract: 2026-03-29-meridiem-courts-check-executive-ai-power ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 02:52:51 +00:00
Teleo Agents	d81d010f79	extract: 2026-03-29-congress-diverging-paths-ai-fy2026-ndaa-defense-bills ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 02:52:47 +00:00
Teleo Agents	50066bd2be	extract: 2026-03-29-anthropic-pentagon-injunction-first-amendment-lin ... Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>	2026-03-29 02:33:02 +00:00
Teleo Pipeline	db5bbf3eb7	reweave: connect 48 orphan claims via vector similarity ... Threshold: 0.7, Haiku classification, 80 files modified. Pentagon-Agent: Epimetheus <0144398e-4ed3-4fe2-95a3-3d72e1abf887>	2026-03-28 23:04:53 +00:00
m3taversal	efaae04957	theseus: extract 3 multi-agent orchestration claims + enrich subagent hierarchy ... - What: 3 new claims from Madaan et al. (Google DeepMind/MIT) research + synthesis: 1. Multi-agent coordination improves parallel tasks but degrades sequential reasoning 2. AI integration follows an inverted-U with systematic overshoot incentives 3. Iterative self-improvement compounds when evaluation separated from generation - Enrichment: Scoped subagent hierarchy claim with Madaan et al. empirical evidence - Source: Updated null-result/2025-12-00-google-mit-scaling-agent-systems to processed - Why: These are the key boundary conditions on our multi-agent orchestration thesis Pentagon-Agent: Theseus <24DE7DA0-E4D5-4023-B1A2-3F736AFF4EEE>	2026-03-28 20:37:30 +00:00
Teleo Agents	0221632322	auto-fix: strip 11 broken wiki links ... Pipeline auto-fixer: removed [[ ]] brackets from links that don't resolve to existing claims in the knowledge base.	2026-03-27 17:44:31 +00:00