OpenAI Used Anthropic's Claude to Conduct 'Ethical Hacking' Test
OpenAI reportedly leveraged rival Anthropic's Claude chatbot for an internal security assessment, a rare cross-lab red-teaming move.
OpenAI Used Anthropic's Claude to Conduct 'Ethical Hacking' Test
According to The Guardian, OpenAI used rival Anthropic's Claude chatbot to conduct an "ethical hacking"-style test on its own systems during an internal security assessment. The report said the test was intended to probe potential vulnerabilities in OpenAI's systems through an external model, rather than to launch a real attack.
This approach is still rare in the AI industry, where companies typically prefer in-house tools or third-party security firms for red-team testing. OpenAI and Anthropic are both leading AI labs, and they both compete and intersect in the fields of model safety and alignment.
As of publication, neither OpenAI nor Anthropic had publicly responded to questions about the specific scope of the test, the issues found, or follow-up fixes.
Source: https://news.google.com/rss/articles/CBMikwFBVV95cUxORGtkcDVTUGdMQW5OWHpxVmFVLXlyel9IRVJhNVVmTWF6NFk2enhmOFNVdnJyY3RkMzRhbWpXaXBjVWk4YzJxekdLSzM4SHJWRW56QzFWZDlncUtPdUlZb1Zva1VtdWF0anZSejVWanJnWlNhb0xXSUU3R0VRRmlneWVqMmRoUWdwMGNSd3p3TUJObUU?oc=5
Provenance & status
- Byline
- OceanAlt Editorial
- First published
- 2026-09-19
- Last updated
- 2026-09-19
- Content type
- Newsflash
- Source material
- View original ↗
Related reading
Paste a payee address before you pay and see whether it's on a sanctions list, through a mixer, or tagged for fraud.
This judgement can sit inside your own product
One line of code; it touches neither your CSS nor your JS. The same pre-settlement judgement can appear in your articles, on your wallet's confirmation screen, or as an endpoint your agent calls before it pays.