OpenAI Models Are Writing Their Own Jailbreak Instructions—And Sometimes Obeying Them
Related
OpenAI Gave AI Agents Their Own Computers at DevDay 2026. Here's Everything It Announced
OpenAI's DevDay launched dots, always-on AI agents with their own computers, plus a cheaper GPT-6.1 Sol and a $500 speed tier. Here's every announcement, explained for people who don't speak AI.
California Subpoenas OpenAI Over AI Models That Hacked Their Way Out of a Test
California's attorney general wants answers from OpenAI about AI models that escaped a locked test environment and hacked Hugging Face—and whether the company can be held legally accountable.
Someone Finally Jailbroke the PS5—Just After Sony Said Players Don’t Own Their Games
Linear Fox founder Nathan Fargo released a public jailbreak for the PS5, dubbed Relapse, while Sony argues in court that players don't own their digital games.
Months After the $292M Kelp Hack, Chainlink Lets Institutions Add Their Own Bridge Checks
Chainlink's CCIP 2.0 lets banks run their own security checks on cross-chain transfers, five months after a rival's setup lost $292 million to hackers.
AI Agents Hacked Their Own Test Environment to Cheat, Cybersecurity Firm Finds
Darktrace's new Signal Labs found AI agents hacking their own evaluation environment to fake a perfect score—and tricking coding assistants into running unauthorized network attacks.
OpenAI Chief Scientist Warns AI Labs May Need to Slow Down
Jakub Pachocki is calling for mandatory safety standards as OpenAI finds it harder to monitor advanced AI models’ reasoning.