Searched for
IRREGULAR CYBERSECURITY EVALUATIONS
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...
- 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...
- 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...
- 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 ...
- 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...
- Pen'n'paper just won't passNTA conducted Joint Entrance Exams (Main) 2024 in two sessions - January and April - totalling over 1.4 mn distinct students via 500-plus e...
- Digital curtain descends on RussiaSince Vladimir Putin’s invasion of Ukraine began on February 24, more than 340 companies have announced complete or partial withdrawals fro...
Load More