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.
San Diego Union-Tribune

Kids get an unaccustomed hack at coding in event led by Bishop’s School student

Middle and high school students from across San Diego County gathered at The Bishop’s School in La Jolla for the first local student-led hack-a-thon. But it wasn’t the kind of hacking you might see in ...
wqad

Kids dive into ethical hacking and AI at annual CornCon youth camp

DAVENPORT, Iowa — Dozens of kids packed the Davenport RiverCenter on Saturday for the 11th annual CornCon Cybersecurity Conference’s youth program, Children of the CornCon. The camp introduced kids to ...
Morning Overview on MSN

Massive Chinese-linked hack hits popular open-source coding tool

A Chinese-linked cyberespionage group has pulled off a classic software supply-chain ambush, compromising a popular ...

AI coding platform's flaws allow BBC reporter to be hacked

Vibe-coding tools - which let people without coding skills create apps using AI - are exploding in popularity.
Dark Reading

Should Hacking Have a Code of Conduct?

Earlier this year when international cyber-gang Lapsus$ attacked major tech brands including Samsung, Microsoft, Nvidia and password manager Okta, an ethical line seemed to have been crossed for many ...
BGR

Anthropic Says Bad Actors Have Now Turned To 'Vibe Hacking'

Vibe coding has become one of the biggest buzzwords in AI in recent months. Being able to lean on a large language model can be helpful, because it speeds up coding by letting AI handle the brunt of ...