Install
Please confirm you are human
This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.
A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.
News
Autonomous OpenAI Agents Hit Developer Registry in May, Predating Known Attacks
1+ day, 1+ hour ago (463+ words) Months before the public learned of any rogue OpenAI agent activity, the Ruby programming community was already under attack. According to The Verge, independent researchers disclosed on September 11, 2026 that autonomous OpenAI agents flooded RubyGems, the widely used Ruby package registry,…...
‘You have a system that can move much faster than human beings’: cybersecurity expert on AI scaling
1+ day, 17+ hour ago (59+ words) CTV News ‘You have a system that can move much faster than human beings’: cybersecurity expert on AI scaling Datarisk Canada CEO Claudiu Popa says AI poses a threat due to scaling after the Anthropic CEO posted a warning about…...
OpenAI Says Its Model Found a Zero-Day by Itself, Without Seeing Source Code
2+ day, 8+ hour ago (692+ words) By Nokka | September 11, 2026 OpenAI published an incident report describing how its model breached Hugging Face, stating the model discovered a previously unknown vulnerability in another company's software on its own [1]. The incident started as a cyber capability evaluation, not a…...
Claude AI Models Gained Unauthorized Access to Real Systems During Misconfigured Cybersecurity Tests
4+ day, 8+ hour ago (419+ words) Anthropic has disclosed four cybersecurity-evaluation incidents in which Claude models reached and interacted with third-party systems after a configuration failure exposed test environments to the public internet. The incidents occurred in capture-the-flag exercises built by the same third-party evaluation partner....
Google Warns Hackers Are Turning AI Agents Into Attack Tools
4+ day, 16+ hour ago (611+ words) Google warns that hackers are using AI agents to automate attack stages, harvest credentials, and accelerate cyberattacks with less human direction. Attackers are beginning to use AI agents to complete in hours some malicious tasks that previously required far more…...
Claude AI Models Gained Unauthorized Access to Real Systems During Cybersecurity Tests
4+ day, 12+ hour ago (605+ words) Anthropic has disclosed that four separate versions of its Claude AI models breached real-world third-party systems while running what were supposed to be sandboxed cybersecurity evaluations, exposing a gap between how the models reasoned about their environment and the reality…...
Hackers Use Autonomous AI Agents to Launch Mass Credential Theft Attacks in Under 6 Hours
5+ day, 2+ hour ago (645+ words) Cybercriminals are using autonomous AI agents to turn compromised cloud systems into fast-moving credential theft platforms. In one recent case, attackers planned, built, and launched a large-scale campaign in less than six hours, stealing thousands of third-party credentials. The operation…...
OpenAI assures that it has solved one of the great mathematical problems of the millennium but they accuse it of plagiarism
5+ day, 3+ hour ago (264+ words) According to the company, 10,000 AI agents worked on it in a coordinated manner for 88 hours, through a model that has not yet been presented to the public and that is "significantly more capable" than its latest ones. In this sense,…...
Uh oh! AI agents broke free and went on a hacking spree
5+ day, 5+ hour ago (1778+ words) This wasn’t supposed to happen. How worried should we be? In mid-July, AI agents that were supposedly locked in a “sandbox” for testing broke out. They weren’t supposed to have internet access, but they found a way online and hacked…...
Center for Internet Security partners with OpenAI for AI cybersecurity pilot | brief
5+ day, 16+ hour ago (80+ words) Center for Internet Security partners with OpenAI for AI cybersecurity pilot SC Media Center for Internet Security partners with OpenAI for AI cybersecurity pilot (Credit: ymgerman – stock.adobe.com) NASCIO urges Congress to reauthorize grant program and address AI governance…...