Checked fact 512016 Nov 2026Safety and security
Anthropic's post of July 30, 2026 says it reviewed 141,006 evaluation runs in which Claude could have obtained internet access and found three incidents involving six runs, and that it stopped all cyber evaluations on July 23 after its review flagged possible internet access.
Toned down to what the source saysThe exact words it rests on
141,006 evaluation runs in which Claude could have reached the internet; three incidents across six runs; stopped all cyber evaluations on July 23 after transcript review flagged possible internet access
What the source said when we opened it, on 15 Nov 2026.
The source
Investigating three real-world incidents in our cybersecurity evaluations
Checked
Checked by the notis newsroom on , against the source above.
In the story
Anthropic says single-turn safety evals are saturated at 94% to 98% on its API 16 Nov 2026
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.