2026-02-01
‘It exploded before anyone thought to check whether the database was properly secured.’
404 Media
A researcher says an exposed Moltbook database could have let anyone take control of the site's AI agents and post anything; the database has since been secured
‘It exploded before anyone thought to check whether the database was properly secured.’ — Moltbook is a “social media” …
2024-12-22
APpaREnTLy THiS iS hoW yoU JaIlBreAk AI — Anthropic created an AI jailbreaking algorithm that keeps tweaking prompts until it gets a harmful response. — 🔗 www.404media.co/apparently-t...
404 Media
Researchers at Anthropic, Oxford, Stanford, and MATS create Best-of-N Jailbreaking, a black-box algorithm that jailbreaks frontier AI systems across modalities
ABSTRACT We introduce Best-of-N (BoN) Jailbreaking … Markus Kasanmascheff / WinBuzzer : y0U hA5ε tU wR1tε l1Ke tHl5 to Break GPT-4o, Gemini Pro and Claude 3.5 Sonnet AI Safety Meas...
2024-12-21
APpaREnTLy THiS iS hoW yoU JaIlBreAk AI — Anthropic created an AI jailbreaking algorithm that keeps tweaking prompts until it gets a harmful response. — 🔗 www.404media.co/apparently-t...
404 Media
Researchers at Anthropic, Oxford, Stanford, and MATS create Best-of-N Jailbreaking, a black-box algorithm that jailbreaks frontier AI systems across modalities
New research from Anthropic, one of the leading AI companies and the developer of the Claude family of Large Language Models …