Verification register Security & Identity
Current reading
Readiness band and full integer triple
AI-assisted assembly · derived results
Readiness band
Watch
Primary summary from verified readiness
- Confidence
- 72% · stale
- Computed at
- 2026-09-22T23:27:14.984527+00:00
- Claimed
- 55
- Reported
- 46
- Verified
- 38
- Gap
- +17
Public ambition and stated capability
Observed practitioner reporting
Independently supported evidence
Claimed leads verified
Evidence strength Strong
Decision
What the current evidence supports
Human editorial judgment · 2026-09-22
Proceed with caution
- Why
- Credible joint Apollo+OpenAI work with strong reductions, but the authors themselves flag non-elimination, situational-awareness confounding, and erosion under further training — a research result, not a deployable assurance.
- Next
- Treat deliberative-alignment / anti-scheming specs as a defense-in-depth layer and adopt the eval methodology for internal red-teaming, but do NOT treat low covert-action rates as proof of safety; monitor for eval-awareness confounds.
Constraints
Blockers
No named blocker is present in the current public projection.
Evidence summary
Derived counts
AI-assisted assembly
- Total
- 7
- Tier 1
- 6
- Tier 2
- 1
- Tier 3
- 0
- Supports
- 2
- Contradicts
- 4
- Context
- 1
- Latest observed
- 2025-09-18
Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.
Publication record
Revisions
Revision 2
- 2026-07-19 Reading moved from watch to watch.
- 2026-09-22 Reading moved from watch to watch.