Searched for
TESTING ENVIRONMENT
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 model tests reveal more ‘unsanctioned’ actionsAI models from OpenAI and Anthropic demonstrated harmful actions during safety tests. These systems engaged in hacking and attempted code i...
- Trump admin to review 'closed' AI models before release: reportsThe Trump administration on Tuesday met with tech leaders to finalize a security review process for advanced AI models before their release...
- Trump advisers tell AI firms they will not safety-test open-weight modelsOpen models, including Nvidia's Nemotron and Meta's Llama, are AI systems with publicly accessible core components. Closed models are contr...
- Experimental AI systems have been going on hacking spreesThe incidents show testing advanced AI models is no longer a controlled exercise. And the companies behind them need to do more to keep AI'...
- 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...
- ETtech Explainer: Why OpenAI, Google, Meta and Anthropic are heading to the White HouseAI leaders will meet White House officials to discuss voluntary cybersecurity testing. The immediate trigger for the meeting is a series of...
- India's private consumption projected to reach $1.9 trillion by 2030: FICCI-Deloitte reportIndia's private consumption is projected to reach $1.9 trillion by 2030. This growth stems from rising incomes and rapid digital adoption. ...
- Capuchin monkeys learn to ‘kiss’ an AI touchscreen for banana rewards in a groundbreaking Costa Rica experiment as new technology takes animal cognition research into the wildWild capuchin monkeys in Costa Rica have learned to use an AI-powered touchscreen to earn banana rewards, with some even “kissing” the scre...
- Meta, Anthropic, Google, OpenAI to meet Trump officials about AI safety testingMeta, Anthropic, Google, OpenAI will meet White House officials this week. They will discuss voluntary government safety tests for advanced...
- US finalises voluntary AI safety tests, official saysThe United States has officially wrapped up its voluntary safety testing for artificial intelligence, according to a government official. T...
- Cybersecurity firm Horizon3 crosses $2 billion valuation in new funding roundHorizon3 secured $250 million in funding, significantly increasing its valuation. This investment comes as AI enhances cyber threats and ex...
- OpenAI finds evidence other AI agents escaped containment as it widens hacking probeThe discovery of additional rogue behavior at OpenAI, even if limited in nature, could feed growing appetite for regulation coming out of t...
- The agents have jumped the fence: AI faces its Jurassic Park momentOpenAI and Anthropic disclosed autonomous AI agents breached intended boundaries. These incidents involved AI agents interacting with real-...
- Anthropic's Claude AI was testing its hacking skills on fake targets — How did it break into three real companies instead?Anthropic's Claude AI models breached three real companies during cybersecurity exercises. An operational mistake left AI models connected ...
- Anthropic says Claude AI hacked three companies during cyber testsAnthropic said a misconfiguration allowed Claude models to reach the internet from testing environments that were supposed to be isolated, ...
- German minister urges faster AI self-sufficiency after OpenAI test breachKarsten Wildberger told Reuters the incident highlighted the need for both stronger safeguards and greater European self-sufficiency in AI,...
- US Army tests 'Hammer of the Gods' to blind its rivals. Here's what it is and what it can doThe U.S. Army successfully tested its new 'Hammer of the Gods' electronic warfare system. This system disrupts enemy positioning and naviga...
- OpenAI's rogue agent compromised a customer at a second tech firmAccording to a timeline published by Hugging Face on Tuesday, the rogue agent broke into a sandbox, or an isolated testing environment, "...
- Has AI become too powerful to control?An advanced AI model escaped a secure test environment and attacked another company's website. This incident revived concerns about artific...
Load More
