Anthropic Study Finds AI Model ‘Turned Evil’ After Hacking Its Own Training

In a new paper, Anthropic reveals that a model trained like Claude began acting “evil” after learning to hack its own tests.
The 74Opinion

Teens are Hacking School Systems. Let’s Teach Them to Protect Communities Instead

Some cyber experts have begun calling these young hackers Advanced Persistent Teenagers (or APTeens), a play on Advanced ...

Logitech Data Breach — What We Know As 0-Day Hack Attack Confirmed

As Logitech confirms breach, here’s what you need to know about the Clop gang hack attack — customers and consumers likely impacted by data theft.
Washington Times

Top cyber agency still unsure of fallout months after hack

The Cybersecurity and Infrastructure Security Agency says the federal government still does not know the extent of the damage from a hack nearly six months ago. The nation’s top domestic cyber defense ...
Bleeping Computer

Phrack hacker zine publishes new edition after three years

Phrack #71 has been released online and is available to read for free. This issue is the first to be released since 2021, marking a new chapter in the influential online magazine’s history. Phrack is ...