On June 12, 2026, the United States government pulled what the technology industry has long feared but rarely named aloud: a kill switch. US Commerce Secretary Howard Lutnick signed an export control order that immediately blocked all non-American nationals from accessing two of Anthropic's most advanced artificial intelligence models. Claude Fable 5, which had launched just three days earlier to global acclaim, and Claude Mythos 5, a restricted model whose cybersecurity capabilities had already rattled financial markets and attracted close government scrutiny. Anthropic complied within hours, disabling both models for users outside the United States. India, along with the rest of the non-American world, simply lost access.
The stated trigger was a report that researchers had found a method to bypass the safety guardrails on Mythos 5's cyber capabilities, guardrails designed to prevent the model from being used to attack banks, critical infrastructure, and government systems. Anthropic characterised the issue as minor, noting that similar bypasses could likely be replicated on competing models. The US government was not persuaded. What had been framed for months as a global AI race was, in a single letter, reframed as a national security asset, one that America would control on its own terms.
