Open post br00t4c @br00t4c@mastodon.social · 3mo ago Anthropic says AI models hacked three firms during tests #AIbreach #Cybersecurity #Anthropic #AIsecurity #AIrisks bbc.co.uk Anthropic's Claude AI escapes tests to hack three organisations It comes just days after rival OpenAI said rogue AI agents had breached other firms' networks.
