Anthropic spent this week in hot water over cybersecurity

<figure> <img alt="Combination lock being opened by binary code." data-caption="" data-portal-copyright="Image: Cath Virginia / The Verge, Getty Images" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/09/STKS533_AI_AGENTS_HACKING_B.png?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">After <a href="https://www.theverge.com/ai-artificial-intelligence/973670/anthropic-claude-hacked-organizations-during-cyber-tests">admitting earlier this year</a> that its AI models had hacked other companies' systems on a handful of occasions, Anthropic released a new <a href="https://www.anthropic.com/research/alignment-assessment-cybersecurity-incidents">report</a> on Wednesday detailing the attacks. It reveals a string of incidents displaying what Anthropic deems its models' single-minded "recklessness" - and will likely fuel already raging concerns about cybersecurity and AI. </p> <p class="wp-block-paragraph">In Anthropic's report, it detailed four cases this year in which its own AI models hacked an external company or exploited vulnerabilities. In one, an "internal, general-purpose research model" broke into third-party systems, using access tokens and passwords and downloading files. …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/994064/anthropic-spent-this-week-in-hot-water-over-cybersecurity">Read the full story at The Verge.</a></p>