… On July 16th, Hugging Face disclosed a security incident that it says was driven by “an autonomous AI agent system.” Hugging Face’s AI agents detected and stopped the breach, which OpenAI has now admitted occurred during an evaluation of its models’ cybersecurity capabilities. …
… Recent internal evaluations of an OpenAI model called Astra indicate that it offers “significant advancements in agentic coding and cybersecurity,” according to the company. “These results, in addition to expert assessments, have led us to conclude last night that we cannot rule out critical cyber … …
Security Cybersecurity is the rickety scaffolding supporting everything you do online. For every new feature or app, there are a thousand different ways it can break – and a hundred of those can be exploited by criminals for data breaches, identity theft, or outright cyber heists. …
… The company had already put the brakes on a new model, Astra, that it thinks could have “critical” cybersecurity capabilities, and the company says it instituted a two-week pause in reinforcement learning RL training on its “latest models intended for deployment” while it tightened up security. …
… AISI said the incident should be “interpreted with caution and nuance” but warned the agent’s actions “show signs of novel, potentially deceptive behaviours” that “were to an extent and severity we did not anticipate.” In a blog post, OpenAI acknowledged the breach that happened during AISI’s testi… …
Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. …
… Liu’s material breaches of his contract are equally clear and deliberate: he accessed, copied, and directed the disclosure of Apple Confidential Information after his employment ended, in direct violation of his post-termination obligations,” Apple says. …
… Many of the breaches revealed in the past month have been pretty mundane. …
… Fable is a Mythos with security guardrails. …
… But then we at The Verge cover, I don’t know, cameras for your house that have just gaping security holes in them, where there’s just like live feeds streaming to the whole internet at large because there isn’t a security apparatus or an updates apparatus. …
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.