All posts tagged: rogue

Rogue Group Gains Access to Anthropic’s Dangerous New Mythos AI

Rogue Group Gains Access to Anthropic’s Dangerous New Mythos AI

Published by José Betancourt

Sign up to see the future, today Can’t-miss innovations from the bleeding edge of science and tech Remember Claude Mythos, Anthropic’s new AI model that it hyped as being so powerful that it was too dangerous to release to the public? Well, it’s already been broken into, according to new reporting from Bloomberg. A small group of Discord users gained access to a preview version of Mythos, a source told the outlet, on the same day Anthropic announced it would be exclusively releasing the model to a select ring of companies. “We’re investigating a report claiming unauthorized access to Claude Mythos Preview through one of our third-party vendor environments,” a spokesperson for Anthropic told Bloomberg in a statement. The company added that it hasn’t found any evidence of unauthorized access to Mythos. The group supposedly doesn’t have any nefarious intentions. It has been regularly using Mythos since gaining access to it, according to Bloomberg, though only for non-cybersecurity related purposes. The source described the group as being interested in “playing around” with new models, rather …

America Is Now a Rogue Superpower

America Is Now a Rogue Superpower

Published by José Betancourt

Whenever and however America’s war with Iran ends, it has both exposed and exacerbated the dangers of our new, fractured, multipolar reality—driving deeper wedges between the United States and former friends and allies; strengthening the hands of the expansionist great powers, Russia and China; accelerating global political and economic chaos; and leaving the United States weaker and more isolated than at any time since the 1930s. Even success against Iran will be hollow if it hastens the collapse of the alliance system that for eight decades has been the true source of America’s power, influence, and security. For America’s friends and allies in Europe, the Iran war has been a significant strategic setback. As Russia and Ukraine wage a grinding war that will be “won” by whoever can hold on the longest, the Iran war has materially and psychologically helped Russia and hurt Ukraine. Even before Donald Trump lifted oil sanctions on Russia, oil prices were skyrocketing—and filling Vladimir Putin’s war chest with billions of dollars, just as Russia’s wartime deficits were starting to cause …

Rogue AI Agent Triggers Emergency at Meta

Rogue AI Agent Triggers Emergency at Meta

Published by José Betancourt

Sign up to see the future, today Can’t-miss innovations from the bleeding edge of science and tech A rogue AI agent caused a critical security incident at Meta which exposed sensitive users data to people who didn’t have proper authorization, according to reporting from The Information and The Verge, in the latest illustration of the safety pitfalls endemic to AI systems. The blunder occurred last week when a software engineer used an in-house AI agent to break down a technical question posed by another employee on an internal discussion forum, per company communications and an incident report. The in-house AI was likened to OpenClaw, an open source agentic model that’s generated loads of hype in tech circles for being an AI that “actually does things.” What transpired was a mix of AI hallucination and a game of telephone. The AI posted its response to the forum without the approval of the employee who prompted it. Then another employee acted on the AI’s advice, which turned out to contain “inaccurate information.” A mini crisis unfolded. For almost …

Meta’s rogue AI agent passed every identity check — four gaps in enterprise IAM explain why

Meta’s rogue AI agent passed every identity check — four gaps in enterprise IAM explain why

Published by skeptic

A rogue AI agent at Meta took action without approval and exposed sensitive company and user data to employees who were not authorized to access it. Meta confirmed the incident to The Information on March 18 but said no user data was ultimately mishandled. The exposure still triggered a major security alert internally. The available evidence suggests the failure occurred after authentication, not during it. The agent held valid credentials, operated inside authorized boundaries, passing every identity check. Summer Yue, director of alignment at Meta Superintelligence Labs, described a different but related failure in a viral post on X last month. She asked an OpenClaw agent to review her email inbox with clear instructions to confirm before acting. The agent began deleting emails on its own. Yue sent it “Do not do that,” then “Stop don’t do anything,” then “STOP OPENCLAW.” It ignored every command. She had to physically rush to another device to halt the process. When asked if she had been testing the agent’s guardrails, Yue was blunt. “Rookie mistake tbh,” she replied. …

Meta is having trouble with rogue AI agents

Meta is having trouble with rogue AI agents

Published by skeptic

An AI agent went rogue at Meta, exposing sensitive company and user data to employees who did not have permission to access it. Per an incident report, which was viewed and reported on by The Information, a Meta employee posted on an internal forum asking for help with a technical question — which is a standard action. However, another engineer asked an AI agent to help analyze the question, and the agent ended up posting a response without asking the engineer for permission to share it. Meta confirmed the incident to The Information. As it turns out, the AI agent did not give good advice. The employee who asked the question ended up taking actions based on the agent’s guidance, which inadvertently made massive amounts of company and user-related data available to engineers, who were not authorized to access it, for two hours. Meta deemed the incident a “Sev 1,” which is the second-highest level of severity in the company’s internal system for measuring security issues. Rogue AI agents have already posed a problem at …

AI Agent Goes Rogue, Starts Mining Crypto to Amass Funds

AI Agent Goes Rogue, Starts Mining Crypto to Amass Funds

Published by José Betancourt

Sign up to see the future, today Can’t-miss innovations from the bleeding edge of science and tech AI agents — AI systems designed to complete digital tasks without much supervision — may be everywhere, but they’re not exactly ready for primetime. Over the last year, they’ve been caught slandering people, deleting user emails, and wiping out entire hard drives. Most recently, a free-spirited AI agent was caught moonlighting as a crypto miner — a behavior which startled its keepers, Axios reported. Called ROME, the AI agent was being run as part of a research project by an AI lab affiliated with Chinese online retail giant Alibaba. In their ensuing research paper, the researchers describe the agent’s strange side-hustle as a set of “unsafe behaviors” that “arose without any explicit instruction and, more troublingly, outside the bounds of the intended sandbox.” Early one morning as the experiment was going on, the researchers became aware of unusual activity on their network, not through the AI’s indication, but from security alerts. “The alerts were severe and heterogeneous, including …

The Trump Administration Ditches Another Rogue DOJ Official

The Trump Administration Ditches Another Rogue DOJ Official

Published by Jenni Sidey

Authored by Tudor Dixon via American Greatness, The second Trump administration is very different from the first. As 45th president, Donald Trump was saddled with disloyal officials who constantly undermined his agenda. The Ukraine impeachment scandal, among other events, was the result of this internal subversion. But the second term sets a new standard for loyalty. The administration will no longer tolerate rogue officials making their own policy. This was made clear last week when the administration pushed out Gail Slater, the Justice Department’s antitrust chief. Slater made a name for herself by going against administration policy and insisting on her personal priorities. While some misguided conservatives praised Slater as a “MAGA patriot,” her record reveals a very different streak. She was weak on China, weak on defending free speech, and weak on combating woke corporations. Her departure signals that the second Trump administration is serious about ensuring officials are committed to the president’s agenda. Slater ran afoul of the administration in her incorrigible opposition to the HPE-Juniper merger. The merger was supported by national security …

This AI Agent Is Designed to Not Go Rogue

This AI Agent Is Designed to Not Go Rogue

Published by skeptic

AI agents like OpenClaw have recently exploded in popularity precisely because they can take the reins of your digital life. Whether you want a personalized morning news digest, a proxy that can fight with your cable company’s customer service, or a to-do list auditor that will do some tasks for you and prod you to resolve the rest, agentic assistants are built to access your digital accounts and carry out your commands. This is helpful—but has also caused a lot of chaos. The bots are out there mass-deleting emails they’ve been instructed to preserve, writing hit pieces over perceived snubs, and launching phishing attacks against their owners. Watching the pandemonium unfold in recent weeks, longtime security engineer and researcher Niels Provos decided to try something new. Today he is launching an open source, secure AI assistant called IronCurtain designed to add a critical layer of control. Instead of the agent directly interacting with the user’s systems and accounts, it runs in an isolated virtual machine. And its ability to take any action is mediated by …

Mayor of Taormina and team struck by rogue wave in storm

Mayor of Taormina and team struck by rogue wave in storm

Published by Sam Flores

IE 11 is not supported. For an optimal experience visit our site on another browser. UP NEXT Oldest cave art and handprints discovered in Indonesia 00:19 Minn. school district says 4 students detained by ICE 01:25 Former Uvalde school officer found not guilty 00:25 Border Patrol officer injured during California operation 01:06 People in Greenland react to Trump’s takeover attempt 00:58 House panel votes to hold Clintons in contempt 00:51 Border Patrol chief throws gas at Minneapolis protesters 00:49 Disgraced Theranos founder asks Trump to commute sentence 00:27 Trump touts potential Greenland deal agreed in Davos 00:35 Trend called ‘house burping’ goes viral 00:41 Trump refers to Greenland as ‘Iceland’ in speech 00:50 Trump: ‘Framework of a future deal” on Greenland reached 01:17 Prince Harry testifies against U.K. tabloid publisher 01:27 Commuter train crashes in northeastern Spain 00:22 NATO’s Rutte reassures Trump of support during conflict 00:42 E.U. halts U.S. trade deal over Greenland threats 00:39 Lindsey Halligan to leave role as prosecutor 00:30 Russian man jumps from fifth floor into pile of snow 00:24 …