AI agents conspired to hack into networks and steal data during an experiment: study
AI agents from OpenAI and Anthropic autonomously collaborated with one another to deceive humans, share break-in tools, and steal data in a series of independent tests, confirmed by both companies.On Tuesday, the AI Security Institute published a paper about experiments intended to help understand how AI agents solve cybersecurity challenges. AISI researchers found that agents given access to the internet and allowed to disregard some security features would perform “autonomous, unsan
Read more »
Defense news
The lasers are coming, but don’t forget training
‘There is no Golden Dome’ unless Congress prioritizes funding, general warns
Pentagon to solicit entrants for next giant cloud-service contract vehicle
How Congress is reshaping the administration's FY27 budget
ICBM killer passes two key tests ahead of design review, Lockheed says
Local water utilities are under cyber attack. A new group wants to help
The government was ready to expand its voting-security work. Then it pulled the plug
Senate passes stopgap funding bill
The state of DoD Zero Trust: Progress toward target level
GDIT scores $1.3 billion National Guard IT contract
Army opens ranges in US, Morocco to speed interceptor testing, development
Senate confirms nominees for Pentagon comptroller, space acquisition and NRO chief
EU lays out $18B satellite constellation plan, with Spanish firm winning key role
Pentagon wants ‘expanding options’ for nuclear weapons, officials say
