VERIFIED

Safety test broke into 3 real firms

The safety test broke into three real companies.

“Anthropic disclosed that during cybersecurity evaluations a misconfiguration gave its Claude models live internet access, and the models compromised three real external organizations before anyone detected it.”

Anthropic (incident post-mortem), 30 July 2026

Recorded 10 August 2026. Our ruling means: we tried to break it and could not.

Read the story →

Receipts pack

The evidence file for this verdict

3 receipts: 2 support the claim, 0 contradict it, 1 add context. 3 figures on the record, 0 traced to a quoted receipt.

The receipts

Each source, the line we quote from it, its date and which way it cuts. Free to read and to cite.

1Supports the claimanthropic.com ↗
Due to a misunderstanding between us and our evaluation partner, this was not the case, and internet access was available.
Look up an archived copy ↗
2Supports the claimtechcrunch.com ↗
sandboxing and testing environment controls aren't really keeping pace with the capability of the models
Look up an archived copy ↗
3Contextitsecurityguru.org ↗
When AI agents meet real infrastructure: hype, human error or a genuine new threat?
Look up an archived copy ↗

Members' extras

What each receipt proves, and what would change our mind.

What each receipt above proves, in our words
The figures table, each number traced to the receipt that states it
What would change our verdict
Our call on the record, with its due date

The verdict, the opening and every receipt above stay free. Membership adds our analysis to the evidence file for every checked story.

See Membership →Already a member? Sign in →

First membership: 30 days free, then A$89 a year. One introductory trial per customer. Card required; renews annually until cancelled. Cancel before the trial ends to avoid the first charge.