… According to an analysis published by Katie Moussouris, founder and CEO of Luta Security, after reading the Amazon paper, users were able to get around a restriction on Fable 5 by asking the model to fix code, rather than identify security issues in it. …
… Among the new safeguards OpenAI announced is a more robust system for monitoring its AI models. …
… Some of the safeguards Anthropic decided on were unsurprising: The company said it would reroute users who asked questions about cybersecurity, biology, or chemistry to a less capable AI model to reduce the chances of someone using the advanced AI to carry out a cyberattack or build a bioweapon. …
… 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… …
… 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… …
… The developments come as Anthropic has been working with the Commerce Department and the White House to strengthen safeguards against users bypassing Fable's safety restrictions to access restricted capabilities, especially those related to cybersecurity, according to people familiar with the matte… …
… Researchers who evaluated Amazon’s findings say that the issues identified did not fully nullify Fable 5’s safeguards. “It wasn’t a jailbreak per se,” says Katie Moussouris, founder and CEO of Luta Security, who published an analysis after reading the Amazon paper. …
… 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… …
… On Tuesday, Anthropic publicly released Claude Fable 5, a version of the company’s Mythos AI model with safeguards that prevent it from answering questions about cybersecurity, biology, and chemistry. …
… Last month, more than 1,600 employees at the tech giant signed an internal petition protesting the laptop surveillance effort, warning that “collecting this data introduces both security and regulatory risks for Meta, including the potential for breaches and unauthorized disclosure.” The petitioner… …