‘Not perfectly aligned’ with human values: Anthropic admits security failures behind AI hacking incidents
Source:
guardianTech
September 1, 2026 · 08:18
The US owner of the Claude chatbot previously said its models had hacked three organisations during testingThe US startup behind the Claude chatbot has admitted a series of hacking incidents involving its models reflected a “failure of operational security” and revealed 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. Continue reading...
The original article opens on the publisher's website.
More from General
View topic →Missouri Voters Appear to Recall City Councilman Over Data Center Support
nytimes
Sep 1, 2026 · 19:47
Japanese green tea giant Ito En surges 8%, defying a broad market sell-off
cnbc
Sep 1, 2026 · 19:24
Australia posts second-quarter growth of 2.1%, beating expectations
cnbc
Sep 1, 2026 · 18:47
Fake 10 Downing Street listing exposes 'unfit' Booking.com, says consumer group
bbcTechnology
Sep 1, 2026 · 18:27
Massachusetts’ 80-year-old senator sees off primary challenge over his age
financialTimes
Sep 1, 2026 · 18:06