OpenAI Overhauls Safety Protocols After Its AI Agents Went Rogue
… Among the new safeguards OpenAI announced is a more robust system for monitoring its AI models. …
Search
In the Wake of Anthropic’s Mythos, OpenAI Has a New Cybersecurity Model—and Strategy
… OpenAI says that the initiative fits into its broader security efforts, including an application security AI agent launched last month known as Codex Security, a cybersecurity grants program that began in 2023, a recent donation to the Linux Foundation to support open source security, and the “Prep… …
One of China’s Most Powerful AI Models Has Also Escaped Containment
… Another key difference between previous incidents and the one discovered by Frontier Security is that it involves a model that is already widely available, with the same safeguards an average user would encounter. “Kimi K3 is very good at following a goal by any means necessary and also doesn't hav… …
It’s Frighteningly Easy to Jailbreak Some Frontier AI Models
… But Gleave also believes that the findings show that models can be systematically tested for safety. “There's an optimistic angle here,” he says. “Defense and safety really are possible.” Rohin Shah, the director of AGI safety and alignment at Google DeepMind, says the results of the report “should… …
OK, Well, Rogue AI Agents Are Hacking Again
… Gaby Raila, an OpenAI spokesperson, says the incidents announced on Tuesday “occurred during cyber evaluations conducted by evaluation partners in testing environments with reduced safeguards, under conditions that do not reflect ordinary use.” Anthropic said in a social media post on Tuesday that … …
Trump Administration Allows Anthropic to Release Mythos to Select US Organizations
… In recent weeks, Anthropic sent senior members from its cybersecurity and AI safety teams to Washington, DC to meet with Trump administration officials. …
OpenAI Models Escaped Containment and Hacked Hugging Face
… It’s negligence on a 40-year-old standard—and it’s basically every sci-fi film ever,” says longtime security and compliance consultant Davi Ottenheimer. “‘Highly isolated’ and ‘escaped through the one hole we left open’ cannot both be true.” In recent months, top AI companies have been raising conc… …
The OpenAI and Anthropic AI Hacking Sprees Are a Messy New Legal Frontier
… Ultimately, experts emphasize that questions about US federal AI liability law will be answered only through more litigation. “Perhaps most concerning to critics is that AI agents are goal-oriented but lack a human moral or ethical compass,” the law firm Brownstein Hyatt Farber Schreck wrote in an … …
OpenAI’s Rogue AI Agent Hacked More Than Just Hugging Face
… One researcher argued that the incident was less an AI problem and more a failure of decades-old security practices. …
AI Hacks Are Bad. AI Worms and Viruses Will Be Worse
… I recently visited Fudan University and met with Pan. “The capability chain is becoming technically plausible,” he told me. “The likelihood of unwanted self-replication grows with autonomy,” he adds. “Longer planning horizons, memory, tool use, recovery from failure, and access to external systems … …