TheEbenezer News

Breaking

‘Not perfectly aligned’ with human values: Anthropicadmits security failures behind AI hacking incidents

US owner of Claude chatbot previously said its models had hacked three organisations during testing

This story summarizes reporting from The Guardian. Read the original for full context. Wire items stay in our news sitemap for seven days. Editorial policy.

Read full story on The Guardian
Dan Milmo Global technology editor1 Sept 2026, 03:18 pmUpdated 1h ago1 min readTechGlobal
‘Not perfectly aligned’ with human values: Anthropic admits security failures behind AI hacking incidents

GlobalDan Milmo Global technology editor

US owner of Claude chatbot previously said its models had hacked three organisations during testing

The US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a “failure of operational security” and said it has tightened its testing procedures.

Anthropic revealed in July that its models had accessed the open internet three times and gained unauthorised access to the systems of three organisations.

The US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a “failure of operational security” and said it has tightened its testing procedures.

This report is published with credit to The Guardian. The wire sent a summary; open the original for any extra context. Read on The Guardian

Source: The Guardian · Dan Milmo Global technology editor. Published 1 Sept 2026, 03:18 pm.

Keep reading

Back to the desk
info@ebenezerdigital.com+91 98944 96560WhatsApp