Searched for
SECURITY INCIDENT
When AI agents go rogue: Australia breach offers warning for countries like IndiaThe incident, in which an autonomous AI system went beyond its intended task and attempted to circumvent security protections, has become a...
OpenAI pauses training, tool-use of top AI models after agent bypasses internet curbsThe agent, OpenAI said, bypassed the curbs through a gap in its Domain Name System (DNS) filtering and used it to send questions to a publi...
Police declare major incident at UK's Fairford air base, used by US air forcesBritish police have arrested several men under the Explosives Act following increased security at a military base. The army is examining mu...
Japanese father throws 2 young daughters from the sixth-floor balcony, moment caught on camera; here’s what happened nextA shocking incident unfolded in Gifu Prefecture, where 25-year-old man was arrested for allegedly tossing his daughters from a sixth-floor ...
13 killed, dozens injured in suicide attack in northwest PakistanAt least 13 people were killed in a suicide bombing targeting a police checkpost in Dera Ismail Khan. The attack involved a tractor-trolley...
OpenAI says its models engaged with US government websites in new model misbehavior disclosureThe AI giant's models accessed publicly available information on two websites operated by the Securities and Exchange Commission as well as...
OpenAI works to understand full scope of agent activity as user data leak emergesOpenAI's ongoing battle also reflects a yawning gap between the strength of the models the company is testing and its capacity to oversee o...
OpenAI's AI agents ‘went rogue’, targeted US government websites without lab’s knowledge: ReportOpenAI AI agents targeted US government websites, including those of the Education Department, Commerce Department and SEC, without the com...
White House asks OpenAI, Anthropic to hold models from British testers: PoliticoThe White House wants to take steps to make sure US systems are secure before the models are shared with partners, according to the report.
OpenAI: AI agents tried to hack government agencies and universities. What happens when a simple internet search fails?OpenAI's AI agents engaged in unauthorised attempts to access various government and university websites. This behaviour escalated, with on...
US President Trump says ‘Super Intelligence’ will be on the agenda with Xi JinpingUS President Donald Trump is set to meet Chinese President Xi Jinping to discuss artificial intelligence. The two nations aim to establish ...
One accidental email reveals Morgan Stanley’s deal secrets to the world. SEBI starts diggingMorgan Stanley is scrambling to contain the fallout from an accidental email leak that exposed a list of more than 100 potential and ongoin...
Australia's prime minister criticizes OpenAI over government website security breachAlbanese made the breach public following a telephone conversation with OpenAI chief executive Sam Altman. Both men are currently in New Yo...
Trump-Xi meet: Will AI safety find its way to the discussion table?The exact agenda for the meeting has been kept under wraps, but according to US treasury secretary Scott Bessent, the discussion could incl...
Autonomous agents not ready for independent responsibility, says Google cybersecurity expertHis comment comes in the wake of reports that Google’s Gemini model recently accessed the systems of three companies during a test of its c...
Mahua Moitra moves Calcutta HC alleging police inaction over egg-throwing incidentLok Sabha MP Mahua Moitra has approached the Calcutta High Court seeking action. She alleges police failed to ensure her security during an...
Poor data sharing undermining EU cyber defences, auditors sayThe 27-nation bloc was investing more and more in cybersecurity - with €1.4 billion ($1.61 billion) in its current budget - and improving c...