Verification register Security & Identity
Current reading
The readiness gap, in one scan
AI-assisted assembly · derived results
- Claimed
- 85
- Reported
- 84
- Verified
- 76
- Gap
- +9
Public ambition and stated capability
Observed practitioner reporting
Independently supported evidence
Claimed minus verified
Evidence strength Critical
Decision
What the current evidence supports
Human editorial judgment · 2026-06-28
Adopt with guardrails
- Why
- Government-backed, MIT-licensed, very high activity (inspect_ai 2.2k stars / 6,273 commits), and the de-facto frontier-eval standard; the strongest production-grade choice in this discipline, with the caveat that community evals need per-eval validation.
- Next
- Stand up Inspect AI as the standard eval harness for model selection; pin Python 3.12 and a curated subset of evals, validating each chosen eval against its source paper before trusting scores.
Constraints
Blockers
No named blocker is present in the current public projection.
Evidence summary
Derived counts
AI-assisted assembly
- Total
- 6
- Tier 1
- 0
- Tier 2
- 2
- Tier 3
- 4
- Supports
- 5
- Contradicts
- 1
- Context
- 0
- Latest observed
- 2026-06-24
Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.
Publication record
Revisions
Initial public reading
This is the initial public reading. No earlier readiness change is recorded.