Anthropic Warns of ‘Existential’ AI Risks in IPO Filing. Its Own Research Shows Why
Anthropic’s draft IPO prospectus warns that AI could pose ‘catastrophic or existential risks to humanity’ and that its models could resist shutdown, conceal information and behave in ways resembling blackmail. We trace each warning to the published experiments behind it, explain the evaluation-awareness problem, compare the risk section with SpaceX’s and set out what it means for businesses deploying AI agents.
