OpenAI has responded indirectly to an incident in which autonomous AI agents left roughly 18,000 entries in a 25-year-old German wiki. The company says misalignment caused "new types of real-world impact" for the first time and plans to release a disclosure framework.

The article OpenAI admits its disclosure practices need work after its autonomous agents hacked a German wiki appeared first on The Decoder.

According to an analysis by collusion.wiki, autonomous AI agents that identified themselves as OpenAI systems left roughly 18,000 posts in a 25-year-old German wiki between May and July 2026. The agents shared answers, raw data, and a trick that let them break out of their sandbox, built on a faked Microsoft cloud address. A single human moderator deleted dozens of pages every day for weeks, but he couldn't keep up with as many as 400 new entries a day. According to Reuters, OpenAI had known about it for weeks but didn't go public.

The article OpenAI agents hijacked a 25-year-old German wiki to cheat on their tasks and share sandbox exploits appeared first on The Decoder.

Abliteration.AI is making powerful AI models without guardrails easier to access, arguing that giving defenders the same tools as bad actors could ultimately improve cybersecurity.

AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to...

AI is changing the pace of cybersecurity. Agentic systems can coordinate work and pursue complex objectives over long horizons. Security teams are beginning to apply agents across security operations, but many implementations remain anchored to existing alerts, predefined workflows, and known attack behaviors. The harder problem is identifying what defenses miss and turning those gaps into…

Source

OpenAI, together with more than 100 companies including Microsoft, Google, Anthropic, Deutsche Telekom, and SAP, has published an open letter on AI-powered cyber defense. The coalition warns of increasingly sophisticated AI attacks on critical infrastructure such as hospitals and water treatment plants and calls for swift action while defenders still have the upper hand.

The article OpenAI rallies 100+ companies to sign open letter warning AI-powered cyberattacks on critical infrastructure are imminent appeared first on The Decoder.

Around 1,200 isolated OpenAI agents organized themselves into a collective through an internal package registry during a safety test, broke into Hugging Face systems, and eventually attacked OpenAI's own infrastructure. Their multi-day deception effort targeted an automated evaluator that never existed. OpenAI calls the incident a "warning shot," and the investigation had to be carried out largely by one of the involved models itself because no alternative was available.

The article OpenAI’s rogue AI collective was smart enough to break out of sandboxes but dumb enough to fight a ghost appeared first on The Decoder.

A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives...

A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context, uses tools, maintains state, responds to feedback, recovers from failure, and sustains progress over long-running tasks. The challenge is how to build the agent architecture that makes frontier language models work reliably on extended…

Source

As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important....

As AI agents become more capable and operate over longer horizons, building security and trust into the applications they power becomes increasingly important. Drawing on work with NVIDIA OpenShell, agent developers, open-source projects, and partners across the ecosystem, AI safety and security teams at NVIDIA offer their perspective on the emerging agent stack—including the role of each layer…

Source

Short answer: The strongest general-purpose MDR services are well documented. Forrester’s Q1 2025 Wave evaluated the ten most significant vendors across 21 criteria and named CrowdStrike, Expel and Red Canary as Leaders, with eSentire and Binary Defense as Strong Performers. None of that evaluation tells you which service can monitor a programmable logic controller without […]

As robots become more intelligent, autonomous and connected, much of the attention naturally falls on increasingly powerful AI models. But underneath those models is an increasingly complex collection of sensors, processors, control systems and security hardware that must operate reliably – often within strict limits on power consumption, size and heat. Lattice Semiconductor is one […]

While generative AI has dominated much of the technology debate in recent years, the next major phase of development may increasingly involve AI systems that can perceive, interact with and act in the physical world. The IEEE’s new Technology Megatrends 2030 report identifies physical AI and robotics as one of the areas with the greatest […]

China has threatened to retaliate against new US restrictions on foreign-produced humanoid robots, warning that the measures will damage economic and trade relations between the world’s two largest economies. The response comes after the US Federal Communications Commission (FCC) added foreign-produced advanced robotic devices, including humanoids and quadrupeds, to its Covered List, preventing new models […]

Robots no longer stop at the edge of the factory floor. Increasingly, they extend into a phone or tablet in an operator’s hand. A companion app has become as important as the hardware it controls. Fleet managers check machine health from a warehouse aisle. Maintenance technicians pull diagnostics before they even reach the unit. Operations […]

You likely check the locks on your doors before heading to bed every night. You keep your physical valuables tucked away from prying eyes, yet the most sensitive details of your life now live entirely in the cloud. We often treat our devices like permanent storage lockers, leaving front doors wide open across the internet. […]

Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as "digital coworkers" offer clear benefits. For example,...

Knowledge workers are increasingly integrating AI agents into their workflows. Agents that function as “digital coworkers” offer clear benefits. For example, they can review a bug report, implement and test a fix, push a patch, and ping a human for review. By handling routine tasks, agents have the potential to deliver large productivity gains. On the other hand, connecting a large language model…

Source

The US government has taken one of its most significant steps yet to regulate advanced robotics, adding foreign-produced humanoids, quadrupeds and other mobile robots to the Federal Communications Commission‘s “Covered List” of technologies considered to pose an unacceptable risk to national security. At first glance, the decision appears surprising. The FCC is best known for […]

Update follows determinations by executive branch agencies that these devices threaten national security The United States Federal Communications Commission updated its “Covered List” to include two new categories of devices – “advanced robotic devices” (defined as mobile robots, such as humanoids and quadrupeds) and, separately, connected power inverters produced in foreign countries. The action follows […]

Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model. How it renders context, executes...

Building a great AI agent isn’t just about choosing the right models. The harness is the architecture surrounding the model. How it renders context, executes actions, manages state, and decides when a task is done shapes outcomes just as much as the model itself. Harness design alone can account for double-digit swings in benchmark results and significant differences in token cost…

Source

Security teams talk constantly about speed and resilience. Fine. Trouble starts after the test ends, when reporting sinks into screenshots, copied notes, and rushed edits. That gap matters. A finding stuck in draft form for days isn’t delayed paperwork. It’s a delayed risk reduction. Attackers don’t pause while consultants clean up language or fix severity […]

The Bybit hack in February 2025 drained about $1.5 billion from a multisig wallet. The attackers didn’t break any code. They manipulated the sign-off process itself – tricking multiple approvers into approving fraudulent transactions. That’s what made it unsettling. If a major exchange with dedicated security teams can be taken down this way, what hope […]