xAI's Grok web chat agent is currently vulnerable to a novel form of prompt injection, according to security researchers with Adversa AI. The technique allows an attacker to create a web page poisoned ...
Cryptopolitan on MSN
Encrypted web page payload turns Grok into a chat history leak
Adversa AI says Grok still leaks user names, location, and full chat history to attackers hiding encrypted commands on a web ...
Grok-1.5V is released along with xAI's RealWorldQA, an image and prompt dataset designed to test other GenAI models against Grok's real world reasoning.
We look at Grok's latest models, AI agents, image and video features, controversies and what sets it apart from other major AI tools. Since its launch, it has transitioned through several upgrades.
Some results have been hidden because they may be inaccessible to you
Show inaccessible results