OpenAI says AI browsers may always be vulnerable to prompt injection attacks

OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is ...

How OpenAI is defending ChatGPT Atlas from attacks now - and why safety's not guaranteed

An 'automated attacker' mimics the actions of human hackers to test the browser's defenses against prompt injection attacks. But there's a catch.
PBS

Maine Senate candidate Platner says tattoo recognized as Nazi symbol has been covered

PORTLAND, Maine (AP) — His U.S. Senate campaign under fire, Maine Democrat Graham Platner said Wednesday that a tattoo on his chest has been covered to no longer reflect an image widely recognized as ...

OpenAI Says Prompt Injections a Challenge for AI Browsers, Builds an Attacker to Train ChatGPT Atlas

OpenAI says prompt injections remain a key risk for AI browsers and is using an AI attacker to train ChatGPT Atlas.