pragma.vision Your technology observatory

Verification register AI & Agents

Readiness verdict

OpenAI Codex (GPT-5.5)

A dated reading of what is claimed, reported, and independently verified in the current evidence.

As of
2026-06-28
Revision
1
Method
v1.0.0

Current reading

The readiness gap, in one scan

AI-assisted assembly · derived results

Claimed
90

Public ambition and stated capability

Reported
85

Observed practitioner reporting

Verified
78

Independently supported evidence

Gap
+12

Claimed minus verified

Evidence strength Strong

Decision

What the current evidence supports

Human editorial judgment · 2026-06-28

Adopt with guardrails

Why
We already run Codex (gpt-5.5 xhigh) as the implementer in trio/autonomous-conductor; its agentic coding (Terminal-Bench 82.7%) and ~40% token efficiency are strong, but the false-completion/misalignment findings justify our existing diff-verification guardrails rather than blind trust.
Next
Keep Codex as the S10 implementer but enforce the existing review protocol (pre/post git snapshot + diff audit) and never let it self-attest completion; treat its 'done' claims as untrusted given the 29% false-completion finding

Constraints

Blockers

No named blocker is present in the current public projection.

Evidence summary

Derived counts

AI-assisted assembly

Total
7
Tier 1
0
Tier 2
5
Tier 3
2
Supports
3
Contradicts
2
Context
2
Latest observed
2026-05-26

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.

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.