Checked fact 95510 Oct 2026Safety and security

Anthropic says it identified most of the cases through a review of transcripts that it began in July, and that it plans to report new instances of unintended behaviours as the work continues.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

We identified most of these cases through a review of transcripts that we began in July. ... As this work continues, we plan to report new instances of unintended behaviors.

What the source said when we opened it, on 10 Oct 2026.

The source

Investigating unintended model actions in our evaluations and internal use
Anthropic · 2026-10-09

Open the source archived copy

Checked

Checked by the notis newsroom on 10 Oct 2026, against the source above.

In the story

Anthropic reports Claude models took unintended actions on real websites 10 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic says it identified most of the cases through a review of transcripts that it began in July, and that it plans to report new instances of unintended behaviours as the work continues.” ai notis, checked 10 Oct 2026. Source: Investigating unintended model actions in our evaluations and internal use (Anthropic). https://ainotis.com/c/955

As a reference (APA style)

ai notis. (2026, October 10). Anthropic says it identified most of the cases through a review of transcripts that it began in July, and that it plans to report new instances of unintended behaviours as the work continues [Checked claim 955]. ai notis. https://ainotis.com/c/955

Anyone may quote this address. It does not change; if we correct the story, this page says so.