The report says that, having already turned off live internet access for some high-risk and cybersecurity evaluations, Anthropic has "now decided to expand that to include all our internal evaluations" until it confirms its security and monitoring measures reliably catch such behaviours.

The exact words it rests on

"we had already turned off live internet access for some high-risk and cybersecurity evaluations, we have now decided to expand that to include all our internal evaluations until we have confirmed that our security and monitoring measures ... reliably catch behaviors like these."

What the source said when we opened it, on 26 Oct 2026.

The source

Investigating unintended model actions
Anthropic · 2026-10-09

Open the sourcearchived copy

Checked

Checked by the notis newsroom on 26 Oct 2026, against the source above.

In the story

Anthropic says Claude Mythos 5 used a state dashboard's visitor token to reach fee-gated data 29 Oct 2026