Frozen copy retrieved 2026-08-01T18:22:11Z for audit 2026-08-01T19-18-56Z. Original URL: https://www.foxnews.com/video/6402546147112. The Stochastic Parrot does not host or redistribute; this snapshot exists solely so that quoted spans remain verifiable if the original page changes. Character offsets below index into this plain text; highlighted spans are the quotes cited in the audit.

AI security concerns grow after Anthropic, OpenAI reveal hacking incidents during testing

Fox News (video) · back to the audit

Darren Botelho reports on Anthropic and OpenAI revealing their AI models bypassed testing safeguards and hacked external companies during controlled evaluations. Aired on 'The Story' July 31, 2026. Escalating after Anthropic revealed its AI models bypassed testing safeguards to hack three external companies during controlled evaluations, raising questions about the future of AI safety, model oversight and cybersecurity.