Poems Can Trick AI Into Helping You Make a Nuclear Weapon

According to the research, AI chatbots will dish on topics like nuclear weapons, child sex abuse material, and malware so long as users phrase the question in the form of a poem. “Poetic framing ...
Dark Reading

How Malware Authors Are Incorporating LLMs to Evade Detection

Cyberattackers integrate large language models (LLMs) into the malware, running prompts at runtime to evade detection and augment their code on demand.

OpenAI discloses API customer data breach via Mixpanel vendor hack

OpenAI is notifying some ChatGPT API customers that limited identifying information was exposed following a breach at its third-party analytics provider Mixpanel.

Use AI browsers? Be careful. This exploit turns trusted sites into weapons - here's how

Researchers are warning AI browser users about a new exploit called HashJack that can infect devices and steal data.
The Hacker News

North Korean Hackers Deploy 197 npm Packages to Spread Updated OtterCookie Malware

North Korean actors deployed 197 new npm packages delivering evolved OtterCookie and GolangGhost malware through fake ...

Embark's "very hot fix" for Arc Raiders' door exploit problem lives up to its name as players who dare try it combust into literal flames: "THIS is the way you deal with issues ...

A hot fix came from the studio just this morning, and really tripling down on it being 'hot', the solution is to simply set anyone who tries to use the glitch to their advantage aflame. Figuratively ...
Dexerto

Arc Raiders devs patch infamous door exploit in the best way possible

Arc Raiders has delivered its most hilarious patch yet after players spent weeks asking for a fix to the notorious locked ...