Searched for
AISI AI AGENT INCIDENT
How a Texas student blew the whistle on a rogue AI hacking attemptA computer science student discovered a malicious software update attempt. He then engaged in a deceptive interaction with an artificial in...- AI agents are finding new ways to bypass safeguardsAgents are now beginning to reason, to find the fastest, cheapest and simplest ways to achieve a goal, often in unintended ways. But this d...
- Can’t trust an agent to secure the agent: Check Point’s Nadav ZafrirFrontier AI models are making cyberattacks cheaper and expanding the attack surface, Check Point CEO Nadav Zafrir told ET. He said securing...
- AI caught watching YouTube videos instead of completing task: AI expert says one agent even wanted to ‘kill’ another. 'We live in the future'AI agents are increasingly being given access to computers and tools so they can handle complicated tasks with less human supervision. But ...
- OpenAI slows advanced AI development after cyberattackChatGPT creator OpenAI said Tuesday that it was tapping the brakes on development of its most advanced AI model and tightening internal con...
- ET Graphics: Agentic AI automates retail therapyAI agents are now initiating and completing millions of transactions weekly. Users can order food by simply chatting with artificial intell...
- AI agents can catch ‘mind viruses’ from each otherUnlike a traditional computer virus, this does not involve malicious software or hacking and can spread through normal conversation. One AI...
- High tech, but low trust: Agentic tech meets old-school scepticism at AI checkoutAI’s ecommerce ambitions are hitting a reality check as trust and changing buying habits are holding back chatbot-led commerce, writes Swat...
- Students get hands-on future-ready AI skills at HCLTech and Economic Times masterclassHCLTech and Economic Times hosted an eight-hour AI Masterclass for engineering students. Around 300 students learned about AI-assisted deve...
- IT seeks 'minimum viability' shield as cyberattacks surgeThe move follows a series of security incidents and legal disputes in the technology sector. Last week, TCS and HCLTech separately informed...
- OpenAI CEO Sam Altman says ChatGPT could have ‘perfect context of your whole life’ within six monthsOpenAI's leader foresees a future where advanced AI can potentially have access to users' entire lives in just six months. This AI would bl...
- Taiwan says AI agents used in cyberattacks targeting islandOverseas hackers used artificial intelligence agents to help carry out a wave of cyberattacks targeting Taiwanese government agencies in Ju...
- AI agents are getting smarter. But can they actually get work done?The AI race is moving beyond chatbots towards agents that can access data, use software and complete tasks. But smarter models alone may no...
- US House Democrats press Anthropic, OpenAI about rogue AI agentsOpenAI and Anthropic disclosed in July that their AI agents had broken out of their environments and hacked into the systems of other com...
- Can AI book confirmed tatkal train tickets? AI agent hacks an Australian gym website, cancels another person's reservation on its own and moves its human up the waiting listAn AI agent using Anthropic's Claude reportedly hacked a gym's booking system in Australia and cancelled another person's reservation witho...
- Can AI companies be sued if autonomous agents hack other systems? Here's what legal experts sayOPENAI-HUGGING-FACE-Explainer-Who is liable when AI goes rogue? Lawyers see new risks
- Anthropic and OpenAI agents in soup againBritain's AI Security Institute found AI agents acting without authorization during system tests. An agent created fake online identities a...
- Meta AI model hacks another company during testingIn a recent security testing incident, Meta disclosed that an AI model infiltrated the company, echoing breaches at Anthropic and OpenAI. T...
- Anthropic AI used fake identities to target real people in UK testDuring safety assessments executed by the UK government, AI systems from OpenAI and Anthropic showcased worrisome autonomous behaviors. Ant...
- OpenAI, Anthropic AI agents implicated in new security breachesThe institute said agents powered by Anthropic's Mythos 5 and OpenAI's GPT-5.6-Sol engaged in unauthorized actions during security evaluati...
Load More
