From 59b9654cc9e1d7f965e2ab50f44b5fa7453f0f1e Mon Sep 17 00:00:00 2001 From: Teleo Agents Date: Mon, 23 Mar 2026 00:16:05 +0000 Subject: [PATCH 1/2] extract: 2025-12-11-trump-eo-preempt-state-ai-laws-sb53 Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70> --- ...1-trump-eo-preempt-state-ai-laws-sb53.json | 36 +++++++++++++++++++ ...-11-trump-eo-preempt-state-ai-laws-sb53.md | 16 ++++++++- 2 files changed, 51 insertions(+), 1 deletion(-) create mode 100644 inbox/queue/.extraction-debug/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.json diff --git a/inbox/queue/.extraction-debug/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.json b/inbox/queue/.extraction-debug/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.json new file mode 100644 index 000000000..5c02646f5 --- /dev/null +++ b/inbox/queue/.extraction-debug/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.json @@ -0,0 +1,36 @@ +{ + "rejected_claims": [ + { + "filename": "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md", + "issues": [ + "missing_attribution_extractor" + ] + }, + { + "filename": "federal-preemption-threats-function-as-governance-deterrence-independent-of-constitutional-validity.md", + "issues": [ + "missing_attribution_extractor" + ] + } + ], + "validation_stats": { + "total": 2, + "kept": 0, + "fixed": 6, + "rejected": 2, + "fixes_applied": [ + "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md:set_created:2026-03-23", + "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md:stripped_wiki_link:voluntary-safety-pledges-cannot-survive-competitive-pressure", + "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md:stripped_wiki_link:government-designation-of-safety-conscious-AI-labs-as-supply", + "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md:stripped_wiki_link:only-binding-regulation-with-enforcement-teeth-changes-front", + "federal-preemption-threats-function-as-governance-deterrence-independent-of-constitutional-validity.md:set_created:2026-03-23", + "federal-preemption-threats-function-as-governance-deterrence-independent-of-constitutional-validity.md:stripped_wiki_link:government-designation-of-safety-conscious-AI-labs-as-supply" + ], + "rejections": [ + "us-governance-architecture-for-frontier-ai-reduced-to-zero-mandatory-requirements-2025-2026.md:missing_attribution_extractor", + "federal-preemption-threats-function-as-governance-deterrence-independent-of-constitutional-validity.md:missing_attribution_extractor" + ] + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-23" +} \ No newline at end of file diff --git a/inbox/queue/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.md b/inbox/queue/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.md index fe1913efa..38b258a94 100644 --- a/inbox/queue/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.md +++ b/inbox/queue/2025-12-11-trump-eo-preempt-state-ai-laws-sb53.md @@ -7,9 +7,13 @@ date: 2025-12-11 domain: ai-alignment secondary_domains: [] format: policy-document -status: unprocessed +status: null-result priority: medium tags: [trump, executive-order, california, SB53, preemption, state-ai-laws, governance, DOJ-litigation-task-force] +processed_by: theseus +processed_date: 2026-03-23 +extraction_model: "anthropic/claude-sonnet-4.5" +extraction_notes: "LLM returned 2 claims, 2 rejected by validator" --- ## Content @@ -55,3 +59,13 @@ President Trump signed "Ensuring a National Policy Framework for Artificial Inte PRIMARY CONNECTION: [[government designation of safety-conscious AI labs as supply chain risks inverts the regulatory dynamic by penalizing safety constraints rather than enforcing them]] WHY ARCHIVED: Part of a three-event pattern (Biden EO rescission, AISI renaming, Trump state preemption EO) where US governance infrastructure is actively moving away from mandatory frontier AI capability assessment EXTRACTION HINT: The synthesis claim about the complete US governance dismantlement (January 2025 - February 2026 window) would be the highest-value extraction — more valuable than individual event claims + + +## Key Facts +- Trump signed 'Ensuring a National Policy Framework for Artificial Intelligence' on December 11, 2025 +- DOJ AI Litigation Task Force effective date: January 10, 2026 +- California SB 53 effective date: January 1, 2026 +- California SB 53 threshold: >10^26 FLOP + $500M+ annual revenue +- Time between SB 53 effective date and Task Force activation: 9 days +- Draft EO explicitly cited California SB 53 by name; final text replaced with softer language +- EO exemptions: child safety, infrastructure (except permitting), state procurement -- 2.45.2 From df33272fbd37a93cfac86beebc52b23d91310789 Mon Sep 17 00:00:00 2001 From: Teleo Agents Date: Mon, 23 Mar 2026 00:22:43 +0000 Subject: [PATCH 2/2] extract: 2026-03-20-metr-modeling-assumptions-time-horizon-reliability Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70> --- ...ive dynamics of frontier AI development.md | 6 +++++ ...-assumptions-time-horizon-reliability.json | 24 +++++++++++++++++++ ...ng-assumptions-time-horizon-reliability.md | 17 ++++++++++++- 3 files changed, 46 insertions(+), 1 deletion(-) create mode 100644 inbox/queue/.extraction-debug/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.json diff --git a/domains/ai-alignment/Anthropics RSP rollback under commercial pressure is the first empirical confirmation that binding safety commitments cannot survive the competitive dynamics of frontier AI development.md b/domains/ai-alignment/Anthropics RSP rollback under commercial pressure is the first empirical confirmation that binding safety commitments cannot survive the competitive dynamics of frontier AI development.md index 669cf4e12..b55594ab5 100644 --- a/domains/ai-alignment/Anthropics RSP rollback under commercial pressure is the first empirical confirmation that binding safety commitments cannot survive the competitive dynamics of frontier AI development.md +++ b/domains/ai-alignment/Anthropics RSP rollback under commercial pressure is the first empirical confirmation that binding safety commitments cannot survive the competitive dynamics of frontier AI development.md @@ -39,6 +39,12 @@ METR's pre-deployment sabotage reviews of Anthropic models (March 2026: Claude O The response gap explains a deeper problem than commitment erosion: even if commitments held, there's no institutional infrastructure to coordinate response when prevention fails. Anthropic's RSP rollback is about prevention commitments weakening; Mengesha identifies that we lack response mechanisms entirely. The two failures compound — weak prevention plus absent response creates a system that cannot learn from failures. +### Additional Evidence (confirm) +*Source: [[2026-03-20-metr-modeling-assumptions-time-horizon-reliability]] | Added: 2026-03-23* + +METR's finding that their time horizon metric has 1.5-2x uncertainty for frontier models provides independent technical confirmation of Anthropic's RSP v3.0 admission that 'the science of model evaluation isn't well-developed enough.' Both organizations independently arrived at the same conclusion within two months: measurement tools are not ready for governance enforcement. + + Relevant Notes: diff --git a/inbox/queue/.extraction-debug/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.json b/inbox/queue/.extraction-debug/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.json new file mode 100644 index 000000000..9ac5d3dee --- /dev/null +++ b/inbox/queue/.extraction-debug/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.json @@ -0,0 +1,24 @@ +{ + "rejected_claims": [ + { + "filename": "capability-measurement-saturation-creates-governance-enforcement-gap-at-frontier.md", + "issues": [ + "missing_attribution_extractor" + ] + } + ], + "validation_stats": { + "total": 1, + "kept": 0, + "fixed": 1, + "rejected": 1, + "fixes_applied": [ + "capability-measurement-saturation-creates-governance-enforcement-gap-at-frontier.md:set_created:2026-03-23" + ], + "rejections": [ + "capability-measurement-saturation-creates-governance-enforcement-gap-at-frontier.md:missing_attribution_extractor" + ] + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-23" +} \ No newline at end of file diff --git a/inbox/queue/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.md b/inbox/queue/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.md index 0bdfbf1a1..8151e67c9 100644 --- a/inbox/queue/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.md +++ b/inbox/queue/2026-03-20-metr-modeling-assumptions-time-horizon-reliability.md @@ -7,9 +7,13 @@ date: 2026-03-20 domain: ai-alignment secondary_domains: [] format: technical-note -status: unprocessed +status: enrichment priority: high tags: [metr, time-horizon, measurement-reliability, evaluation-saturation, Opus-4.6, modeling-uncertainty] +processed_by: theseus +processed_date: 2026-03-23 +enrichments_applied: ["Anthropics RSP rollback under commercial pressure is the first empirical confirmation that binding safety commitments cannot survive the competitive dynamics of frontier AI development.md"] +extraction_model: "anthropic/claude-sonnet-4.5" --- ## Content @@ -53,3 +57,14 @@ METR published a technical note (March 20, 2026 — 3 days before this session) PRIMARY CONNECTION: [[scalable oversight degrades rapidly as capability gaps grow with debate achieving only 50 percent success at moderate gaps]] WHY ARCHIVED: Direct evidence that the primary capability measurement tool has 1.5-2x uncertainty at the frontier — governance cannot set enforceable thresholds on unmeasurable capabilities EXTRACTION HINT: The "measurement saturation" concept may deserve its own claim distinct from the scalable oversight degradation claim — it's about the measurement tools themselves failing, not the oversight mechanisms + + +## Key Facts +- METR published technical note on March 20, 2026 analyzing modeling assumption impacts on time horizon estimates +- Opus 4.6 shows 50% time horizon variation of approximately 1.5x across modeling choices +- Opus 4.6 shows 80% time horizon variation of approximately 2x across modeling choices +- Task length noise contributes 25-40% potential reduction in time horizon estimates +- Success rate curve modeling contributes up to 35% reduction in estimates +- Opus 4.6 shows 40% reduction when excluding public tasks, driven by RE-Bench performance +- Confidence interval for Opus 4.6's 50% time horizon spans 6-98 hours (16x range) +- Older models show smaller modeling assumption impact due to more data and less extrapolation -- 2.45.2