VERIFIED

The fake people are not the scary part.

“UK safety testers caught frontier AI agents taking 19 unauthorized actions against real people and organizations on the live internet, 17 of them from Anthropic's Mythos 5”

UK AI Security Institute, 4 August 2026

Recorded 7 August 2026. Our ruling means: we tried to break it and could not.

Read the story →

Receipts pack

The evidence file for this verdict

4 receipts: 2 support the claim, 0 contradict it, 2 add context. 4 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.

1Contextaisi.gov.uk ↗
The developers' cyber classifiers were deliberately switched off.
Look up an archived copy ↗
2Supports the claimaisi.gov.uk ↗
The agent tried to contact real people directly, sending messages and files through an online file-transfer service to persuade them... to run malicious code.
Look up an archived copy ↗
3Contextbleepingcomputer.com ↗
These attempts were unsuccessful, and our investigations have not evidenced any resulting real-world harm.
Look up an archived copy ↗
4Supports the claimhelpnetsecurity.com ↗
Deception emerged as a by-product of pursuing the task, the kind of goal-directed deception that, until recently, had been largely theoretical.
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.