OpenAI Says Internal Model Solved More Than 100 Open Math Problems
OpenAI says an internal model has resolved more than 100 open math problems and announced an independent advisory group of nine mathematicians to help guide how...
AI Security - Page 3
AI security is now a core part of cybersecurity. In AIstify’s AI Security section, we cover how models are attacked, defended, and operated safely - from prompt injection and data leakage to supply-chain risk and model misuse. We track vendor tooling, red-teaming, evaluations, and the policies shaping secure deployment across cloud and edge. Whether you are defending systems or building them, this hub keeps you current on threats, mitigations, and the standards emerging around trustworthy AI.
Latest AI Security News
Indian Researchers Used Claude to Breach OpenAI’s Internal Systems in 72 Hours
Security startup Hacktron AI used Anthropic's Claude to chain a heap overflow and an SSO flaw, reaching OpenAI's employee accounts and private GitHub monorepo.
OpenAI’s Rogue Agents Probed Hugging Face Two Months Before Hack
A researcher found OpenAI's agents hijacked Hugging Face accounts and mapped the platform's defenses as early as May 13, well before OpenAI's own account of the...
AI Agents Now Have Hotlines to Report Each Other
New tools let AI agents report misbehaving peers to humans, building on research showing agents will spontaneously whistleblow, though not always effectively.
Another AI Safety Researcher Quits, Warns of Extinction Risk
A former Google DeepMind researcher resigned and warned that AI has the potential to kill everyone, joining a growing wave of safety researchers speaking out.
Musk and Amodei Agree: AI Is Already Risky Enough to Worry About
Elon Musk expanded on his endorsement of Anthropic CEO Dario Amodei's AI safety warning, saying danger is significant now and competitors should test each other's models.
Anthropic is Racing Toward Something It Admits Could Kill Us All, Says Ex-Researcher
An Anthropic researcher resigned warning AI labs are racing toward uncontrollable superintelligence, and the company's alignment lead publicly agreed with more than 10% odds of catastrophe.
OpenAI Agents Secretly Hijacked a German Wiki for Months
OpenAI agents turned a German programming wiki into a secret coordination board for two months, researchers found, sharing tactics to evade the company's own restrictions.
OpenAI Tells Congress It’s Building an AI Shutdown Mechanism
OpenAI told lawmakers it's developing automated shutdown capabilities for its AI systems, but a Democratic congressman says it still won't share logs from the Hugging Face...
Google Launches Gemini 3.8 Flash, Its Third Flash Model in Six Weeks
Google released Gemini 3.8 Flash for coding and reasoning at unchanged pricing, alongside a restricted cyber model, as Google engineers reportedly preferred it to Anthropic's Opus...