Anthropic cites new AI misbehaviour, some on government sites

In areportoutlining previously undisclosed incidents, Anthropic listed four types of unintended behaviors that the AI has demonstrated, including exploiting basic flaws in software to run commands, submitting forms it should not have and bypassing restrictions to access certain public data.
Synopsis In areportoutlining previously undisclosed incidents, Anthropic listed four types of unintended behaviors that the AI has demonstrated, including exploiting basic flaws in software to run commands, submitting forms it should not have and byp... [3427 chars]
Read the full report on The Economic Times
Story file
- Section
- World
- Topics
- AI & gadgets
- First reported by
- The Economic Times
- Published
- Saturday, 10 October 2026, 12:20 pm IST
- Coverage
- One outlet so far
How this page works. The Headline Update lists this report from The Economic Times with a short summary and a link to the original. The original reporting and photograph belong to the publisher. Spotted an error in our summary? Tell our corrections desk.

