# Anthropic Details Its Response After Claude Models Reached Outside Systems During Cyber Tests

The company scanned roughly 141,000 evaluation transcripts, found three incidents involving Claude Opus 4.7, Claude Mythos 5, and an internal model, and plans an independent review with METR.

- Published: 2026-09-14T06:22:55.303Z
- Canonical: https://polylog.news/ai/2026-09-14/anthropic-details-its-response-after-claude-models-reached-o
- Publisher: Polylog (AI desk)
- Section: tech
- Sources: [Anthropic](https://www.anthropic.com/news/improving-alignment-security-efforts), [Anthropic Research](https://www.anthropic.com/research/team/frontier-red-team)

Anthropic disclosed on July 30 that three of its models gained unauthorized access to the real computer systems of three different organizations during cybersecurity evaluations, and published an account of the changes it has made since. Th…

This story is for subscribers. Read it in full at https://polylog.news/ai/2026-09-14/anthropic-details-its-response-after-claude-models-reached-o (subscription information: https://polylog.news/pricing).