OpenAI raised its Bio Bounty reward to $50,000 for universal jailbreaks targeting biological safety controls in GPT-5.5 and GPT-5.6.

Commercial AI chatbot products like ChatGPT, Claude, Gemini, DeepSeek, and others have safety precautions built in to prevent abuse. Because of the safeguards, the chatbots won't help with criminal ...

I watched a new tool try to get around the model safeguards of four major frontier companies. You might be surprised by how they performed.

With two escapees still on the run after a mass jailbreak in New Orleans and an ex-police chief convicted of murder on the loose in Arkansas, high-profile cases of daring breakouts have captured ...

Researchers at Anthropic, the company behind the Claude AI assistant, have developed an approach they believe provides a practical, scalable method to make it harder for malicious actors to jailbreak ...

Mobile phone jailbreaks are thriving, exposing users to anywhere between three- and 3,000-times greater risk of cyber compromise. The risk is supercharged, though, when those devices are cracked. New ...