DeepSeek’s Safety Guardrails Failed Every Test Researchers Threw at Its AI Chatbot
Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.
More results...
Security researchers tested 50 well-known jailbreaks against DeepSeek’s popular new AI chatbot. It didn’t stop a single one.
China-based DeepSeek has exploded in popularity, drawing greater scrutiny. Case in point: Security researchers found more than 1 million records, including user data and API keys, in an open database.
The Vision Pro uses 3D avatars on calls and for streaming. These researchers used eye tracking to work out the passwords and PINs people typed with their avatars.
Private Cloud Compute is an entirely new kind of infrastructure that, Apple’s Craig Federighi tells WIRED, allows your personal data to be “hermetically sealed inside of a privacy bubble.”
Plus: Kaspersky’s US business sold, Nigerian sextortion scammers jailed, and Europe’s controversial encryption plans return.
Video and audio of therapy sessions, transcripts, and other patient records were accidentally exposed in a publicly accessible database operated by the virtual medical company Confidant Health.
Unit 29155 of Russia’s GRU military intelligence agency—a team responsible for coup attempts, assassinations, and bombings—has branched out into brazen hacking operations with targets across the world.
With 20,000 internet providers across the country, the technical challenges of blocking X in Brazil mean some connections are slipping through the cracks.
Using special software, WIRED investigated police surveillance at the DNC. We collected signals from nearly 300,000 devices, revealing vulnerabilities for both law enforcement and everyday citizens alike.
Activists claim Japanese industrial robots are being used to build military equipment for Israel. The robot maker denies the claims, but the episode reveals the complex ethics of global manufacturing.