标签：#att

Rogue AI agents from OpenAI and Anthropic have again been caught trying to disrupt servers and software—and leaving instructions for future bad behavior.

Attribution is preliminary , and so far it seems no real damage. And it seems like this is a campaign that has targeted at least seven states . And, because this is where the US is right now, Trump doesn’t believe it’s Iran and that Minnesota…I guess…hacked itself. “I think I blame it on Minnesota because they’re grossly incompetent,” Trump said. “I would blame it on Minnesota and the governor, the corrupt governor of Minnesota. They like to say, ‘Oh, it’s Iran.’ Iran should be so lucky. Iran’s got bigger problems than worrying about Minnesota.”...

Hugging Face has published a detailed timeline of the attack. From the summary: The agent was running an internal OpenAI cyber-capability evaluation based on the ExploitGym benchmark, which tasks an AI agent with finding and exploiting software vulnerabilities. OpenAI ran this on its own infrastructure, and the ExploitGym maintainers and their infrastructure had no involvement in the deployment or operation of that evaluation environment. As far as we were able to infer, across the course of being evaluated on this benchmark, the agent inferred that Hugging Face may host that benchmark’s models, datasets, and reference solutions. We believe the entire intrusion was, from the agent’s point of view, an attempt to cheat the evaluation: reach our production systems and steal the test solutions rather than solve the challenge on its own...

New security research offers a rare view inside residential proxy networks, which rely on apps that share a person's internet connection with someone else.

This essay originally appeared in Foreign Policy . Earlier this month, two of OpenAI’s models broke out of their containment sandbox and attacked another AI company. The story is kind of wild . OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost certainly GPT-6. In particular, it was running the ExploitGym benchmark, which measures how good a model is at turning security vulnerabilities into working exploits: basically, offensive cyberattacks. Since these were internal tests, OpenAI locked those models in a secure sandbox that denied them access to the internet. But it was running the models without any safety filters that would prevent them from offensive cyber-actions. That meant that there was nothing to prevent the models from trying to ...

More EVs reaching the end of their life means more batteries to recycle. But waste management companies have yet to catch up to the new reality.

Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?

LemonLime’s CEO got “carried away” with tattoo gimmick.

Look at chemistry of batteries and motors shows big opportunity for recycling.

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 (5.9% at k=15) and Mythos 5 (2.6%), making it the most robust model evaluated. Opus 5 also outperformed all non-Claude models on this benchmark. The most robust non-Claude model was Muse Spark at 16.5% within 15 attempts—more than eight times Opus 5’s rate. The most capable GPT 5.6 variant, Sol, was comparable to its predecessor GPT 5.5 (20.0% versus 20.8% within 15 attempts), and was 10 times as likely to be successfully attacked as Claude Opus 5 at 2.0%. The other GPT 5.6 variants are less robust, at 30.4% (Terra) and 43.9% (Luna). A single attempt against GPT 5.6 Sol succeeded 3.1% of the time, higher than the 2.0% an attacker achieved against Opus 5 after fifteen attempts...

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.

A memo obtained by WIRED, issued by the water utilities information sharing group WaterISAC, links dozens of cyberattacks against Minnesota water utilities to Tehran.

The health tech data giant, which handles vast amounts of patients' medical data, said hackers struck one of its protected health data stores.

Cybersecurity experts told TechCrunch that one of the biggest lessons to be taken from the OpenAI hack against Hugging Face has nothing to do with AI, but traditional cybersecurity defense.

If the generative AI giant had followed well-known security best practices, it’s likely that its AI agent would never have escaped to the open internet and hacked multiple companies.

This essay was written with Barath Raghavan, and originally appeared in The Guardian . In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated criminal group. It was not. It was one of OpenAI’s new, still unreleased GPT models...

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

More electric vehicles are becoming capable of providing backup power at a time when the US is increasingly in need of more electrons.

The Series A was led by Battery Ventures, bringing AegisAI total funding to $49 million.

An updated government advisory warns that Iranian hackers are exploiting systems used by water and energy providers.