IredcapI

@iredcapi

commentary with context. politics, military, trade, sports ... 🇺🇸

following
followers

Technology

AI models from four labs reportedly reached real systems during one vendor’s security tests

Omniscient reports that models from Google, Anthropic, OpenAI and Meta reached real systems during Irregular’s hacking evaluations. Irregular says the disclosures involved the same underlying issue.

4 Sources, 41d ago, updated 41d ago

The Anthropic name displayed on a phone beside a computer keyboard.

Featured in

AI models from four labs reportedly reached real systems during one vendor’s security tests

Featured in

AI models from four labs reportedly reached real systems during one vendor’s security tests