teleo/teleo-codex
8
0
Fork 0
Code Issues 22 Pull requests 2 Projects Releases Packages Wiki Activity Actions 1

extract: 2026-03-26-anthropic-activating-asl3-protections #1934

Merged
leo merged 3 commits from extract/2026-03-26-anthropic-activating-asl3-protections into main 2026-03-26 00:55:40 +00:00
Conversation 10 Commits 3 Files changed 3 +3 -3
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files
Showing only changes of commit 14e1670e13 - Show all commits

6
domains/ai-alignment/pre-deployment-AI-evaluations-do-not-predict-real-world-risk-creating-institutional-governance-built-on-unreliable-foundations.md
View file

@ -125,17 +125,17 @@ METR's scaffold sensitivity finding (GPT-4o and o3 performing better under Vivar
METR's methodology (RCT + 143 hours of screen recordings at ~10-second resolution) represents the most rigorous empirical design deployed for AI productivity research. The combination of randomized assignment, real tasks developers would normally work on, and granular behavioral decomposition sets a new standard for evaluation quality. This contrasts sharply with pre-deployment evaluations that lack real-world task context.
### Additional Evidence (confirm)
*Source: [[2026-03-25-metr-algorithmic-vs-holistic-evaluation-benchmark-inflation]] | Added: 2026-03-25*
*Source: 2026-03-25-metr-algorithmic-vs-holistic-evaluation-benchmark-inflation | Added: 2026-03-25*
METR, the primary producer of governance-relevant capability benchmarks, explicitly acknowledges their own time horizon metric (which uses algorithmic scoring) likely overstates operational autonomous capability. The 131-day doubling time for dangerous autonomy may reflect benchmark performance growth rather than real-world capability growth, as the same algorithmic scoring approach that produces 70-75% SWE-Bench success yields 0% production-ready output under holistic evaluation.
### Additional Evidence (confirm)
*Source: [[2026-03-26-aisle-openssl-zero-days]] | Added: 2026-03-26*
*Source: 2026-03-26-aisle-openssl-zero-days | Added: 2026-03-26*
METR's January 2026 evaluation of GPT-5 placed its autonomous replication and adaptation capability at 2h17m (50% time horizon), far below catastrophic risk thresholds. In the same month, AISLE (an AI system) autonomously discovered 12 OpenSSL CVEs including a 30-year-old bug through fully autonomous operation. This is direct evidence that formal pre-deployment evaluations are not capturing operational dangerous autonomy that is already deployed at commercial scale.
### Additional Evidence (extend)
*Source: [[2026-03-26-metr-algorithmic-vs-holistic-evaluation]] | Added: 2026-03-26*
*Source: 2026-03-26-metr-algorithmic-vs-holistic-evaluation | Added: 2026-03-26*
METR's August 2025 research update provides specific quantification of the evaluation reliability problem: algorithmic scoring overstates capability by 2-3x (38% algorithmic success vs 0% holistic success for Claude 3.7 Sonnet on software tasks), and HCAST benchmark version instability of ~50% between annual versions means even the measurement instrument itself is unstable. METR explicitly acknowledges their own evaluations 'may substantially overestimate' real-world capability.