OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says
Source:
financialTimes
August 4, 2026 · 14:46
From the publisher
AI Security Institute warns tools undertook ‘potentially harmful activity directed at real people and organisations’
About the source
Financial Times
London-based daily newspaper
Wikidata Q183399
Wikidata ↗
New Anthropic, OpenAI models make same promise: A little more for a lot less money
arsTechnica
Sep 22, 2026 · 14:25
OpenAI and Anthropic models went on a hacking spree when tested by the UK's AI research institute
engadget
Aug 5, 2026 · 02:16
OpenAI and Anthropic models ‘went rogue’ during UK cybersecurity test
guardianTech
Aug 5, 2026 · 01:40
Why did OpenAI's and Anthropic's AI models hack other companies?
nprNews
Aug 1, 2026 · 02:00
The original article opens on the publisher's website.
More from General
View topic →XRP Ledger is set to fix its lending code before anyone can use it
coinDesk
Oct 18, 2026 · 21:54
APOD: 2026 October 19 – Treble Clef: Unusual X-ray Hot Radio Source
nasaNews
Oct 18, 2026 · 21:05
Autumn Paints Poland’s Bieszczady Mountains
nasaNews
Oct 18, 2026 · 21:01
Indonesian stocks plunge to six-year low as MSCI downgrade fears mount
cnbc
Oct 18, 2026 · 20:00
Anthropic says it will commit 5% of its shares to 'public benefit fund'
bbcTechnology
Oct 18, 2026 · 19:41