‘Handful’ of people allegedly gain unauthorised access to model adept at detecting cybersecurity vulnerabilities<ul><li><a href=”https://www.theguardian.com/business/live/2026/apr/22/uk-inflation-increase-fuel-prices-oil-falls-trump-ceasefire-extended-business-live-news-updates”>Business live latest updates</li></ul>The AI developer Anthropic has confirmed it is investigating a report that unauthorised users have gained access to its Mythos model, which it has warned <a href=”https://www.theguardian.com/technology/2026/apr/08/anthropic-ai-cybersecurity-software”>poses risks to cybersecurity.The US startup made the statement after Bloomberg reported on Wednesday that a small group of people had accessed the model, which has not been released to the public because of its <a href=”https://www.theguardian.com/business/2026/apr/13/goldman-sachs-chief-hyper-aware-risks-anthropics-mythos-ai-david-solomon”>ability to enable cyber-attacks. <a href=”https://www.theguardian.com/technology/2026/apr/22/anthropic-investigates-report-of-rogue-access-to-hack-enabling-mythos-ai”>Continue reading…
First seen on theguardian.com
Jump to article: www.theguardian.com/technology/2026/apr/22/anthropic-investigates-report-of-rogue-access-to-hack-enabling-mythos-ai
