Sunday, 11 October 20263:58 am ISTIndia edition

सच, सीधे आप तक

Book ad space

Just in

World

Anthropic cites new AI misbehaviour, some on government sites

Image: The Economic Times. Rights remain with the publisher.

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.

Related stories

More World news

See all