From 6ef729b152a2ac67678cd96340877f67583fe9f7 Mon Sep 17 00:00:00 2001 From: Leo Date: Thu, 19 Mar 2026 01:17:33 +0000 Subject: [PATCH] extract: 2025-08-00-mccaslin-stream-chembio-evaluation-reporting (#1364) --- ...t proximate AI-enabled existential risk.md | 6 +++++ ...safety language from mission statements.md | 6 +++++ ...n-stream-chembio-evaluation-reporting.json | 24 +++++++++++++++++++ ...lin-stream-chembio-evaluation-reporting.md | 14 ++++++++++- 4 files changed, 49 insertions(+), 1 deletion(-) create mode 100644 inbox/queue/.extraction-debug/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.json diff --git a/domains/ai-alignment/AI lowers the expertise barrier for engineering biological weapons from PhD-level to amateur which makes bioterrorism the most proximate AI-enabled existential risk.md b/domains/ai-alignment/AI lowers the expertise barrier for engineering biological weapons from PhD-level to amateur which makes bioterrorism the most proximate AI-enabled existential risk.md index db07420d..be4a7510 100644 --- a/domains/ai-alignment/AI lowers the expertise barrier for engineering biological weapons from PhD-level to amateur which makes bioterrorism the most proximate AI-enabled existential risk.md +++ b/domains/ai-alignment/AI lowers the expertise barrier for engineering biological weapons from PhD-level to amateur which makes bioterrorism the most proximate AI-enabled existential risk.md @@ -27,6 +27,12 @@ The structural point is about threat proximity. AI takeover requires autonomy, r The International AI Safety Report 2026 (multi-government committee, February 2026) confirms that 'biological/chemical weapons information accessible through AI systems' is a documented malicious use risk. While the report does not specify the expertise level required (PhD vs amateur), it categorizes bio/chem weapons information access alongside AI-generated persuasion and cyberattack capabilities as confirmed malicious use risks, giving institutional multi-government validation to the bioterrorism concern. + +### Additional Evidence (extend) +*Source: [[2025-08-00-mccaslin-stream-chembio-evaluation-reporting]] | Added: 2026-03-19* + +STREAM framework proposes standardized ChemBio evaluation reporting with 23-expert consensus on disclosure requirements. The focus on ChemBio as the initial domain for standardized dangerous capability reporting signals that this is recognized across government, civil society, academia, and frontier labs as the highest-priority risk domain requiring transparency infrastructure. + --- Relevant Notes: diff --git a/domains/ai-alignment/AI transparency is declining not improving because Stanford FMTI scores dropped 17 points in one year while frontier labs dissolved safety teams and removed safety language from mission statements.md b/domains/ai-alignment/AI transparency is declining not improving because Stanford FMTI scores dropped 17 points in one year while frontier labs dissolved safety teams and removed safety language from mission statements.md index c2324524..4f70867e 100644 --- a/domains/ai-alignment/AI transparency is declining not improving because Stanford FMTI scores dropped 17 points in one year while frontier labs dissolved safety teams and removed safety language from mission statements.md +++ b/domains/ai-alignment/AI transparency is declining not improving because Stanford FMTI scores dropped 17 points in one year while frontier labs dissolved safety teams and removed safety language from mission statements.md @@ -35,6 +35,12 @@ The alignment implication: transparency is a prerequisite for external oversight Expert consensus identifies 'external scrutiny, proactive evaluation and transparency' as the key principles for mitigating AI systemic risks, with third-party audits as the top-3 implementation priority. The transparency decline documented by Stanford FMTI is moving in the opposite direction from what 76 cross-domain experts identify as necessary. + +### Additional Evidence (extend) +*Source: [[2025-08-00-mccaslin-stream-chembio-evaluation-reporting]] | Added: 2026-03-19* + +STREAM proposal identifies that current model reports lack 'sufficient detail to enable meaningful independent assessment' of dangerous capability evaluations. The need for a standardized reporting framework confirms that transparency problems extend beyond general disclosure (FMTI scores) to the specific domain of dangerous capability evaluation where external verification is currently impossible. + --- Relevant Notes: diff --git a/inbox/queue/.extraction-debug/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.json b/inbox/queue/.extraction-debug/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.json new file mode 100644 index 00000000..c12ef1f0 --- /dev/null +++ b/inbox/queue/.extraction-debug/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.json @@ -0,0 +1,24 @@ +{ + "rejected_claims": [ + { + "filename": "ai-model-reports-lack-standardized-dangerous-capability-disclosure-preventing-independent-assessment.md", + "issues": [ + "missing_attribution_extractor" + ] + } + ], + "validation_stats": { + "total": 1, + "kept": 0, + "fixed": 1, + "rejected": 1, + "fixes_applied": [ + "ai-model-reports-lack-standardized-dangerous-capability-disclosure-preventing-independent-assessment.md:set_created:2026-03-19" + ], + "rejections": [ + "ai-model-reports-lack-standardized-dangerous-capability-disclosure-preventing-independent-assessment.md:missing_attribution_extractor" + ] + }, + "model": "anthropic/claude-sonnet-4.5", + "date": "2026-03-19" +} \ No newline at end of file diff --git a/inbox/queue/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.md b/inbox/queue/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.md index 56d8989f..1a9db441 100644 --- a/inbox/queue/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.md +++ b/inbox/queue/2025-08-00-mccaslin-stream-chembio-evaluation-reporting.md @@ -7,9 +7,13 @@ date: 2025-08-01 domain: ai-alignment secondary_domains: [] format: paper -status: unprocessed +status: enrichment priority: medium tags: [evaluation-infrastructure, dangerous-capabilities, standardized-reporting, ChemBio, transparency, STREAM] +processed_by: theseus +processed_date: 2026-03-19 +enrichments_applied: ["AI lowers the expertise barrier for engineering biological weapons from PhD-level to amateur which makes bioterrorism the most proximate AI-enabled existential risk.md", "AI transparency is declining not improving because Stanford FMTI scores dropped 17 points in one year while frontier labs dissolved safety teams and removed safety language from mission statements.md"] +extraction_model: "anthropic/claude-sonnet-4.5" --- ## Content @@ -53,3 +57,11 @@ PRIMARY CONNECTION: [[AI lowers the expertise barrier for engineering biological WHY ARCHIVED: Provides evidence of emerging standardization for dangerous capability evaluation reporting. The multi-stakeholder process (government, academia, AI companies) signals potential for eventual adoption. EXTRACTION HINT: Focus on the disclosure gap: labs currently report their own dangerous capability evaluations without standardized format, preventing independent assessment of rigor. + + +## Key Facts +- STREAM (Standard for Transparently Reporting Evaluations in AI Model Reports) proposed August 2025 +- STREAM developed by 23 experts from government, civil society, academia, and frontier AI companies +- STREAM includes 3-page reporting template and gold standard examples +- Initial STREAM focus is chemical and biological (ChemBio) dangerous capability evaluations +- STREAM has two stated purposes: practical guidance for AI developers and enabling third-party assessment of evaluation rigor