<p>US cybersecurity researchers who conducted hack say ‘scope of what we could theoretically access was huge’</p><p>Cybersecurity researchers have hacked into OpenAI with the help of Anthropic’s Claude chatbot, in the latest example of <a href="https://www.theguardian.com/technology/2026/aug/26/openai-staff-observed-warning-signs-before-ai-agent-hacking-crusade-caused-global-alarm">security issues</a> at the company.</p><p>A team at a US-based startup compromised a number of OpenAI employees’ Ch