U.S. government allows Anthropic to release restricted 'Mythos' AI model to trusted U.S. organizations
The U.S. government has authorized Anthropic to release a powerful AI model called Mythos to a restricted set of 'trusted' U.S. organizations, suggesting a new government-mediated access tier for frontier AI capabilities. The arrangement implies Mythos has capabilities or risk profiles that warranted export-control-style restrictions on broader release. This represents a notable intersection of national security policy and frontier AI deployment.
Related guides (4)
AI Safety ResearchTopic guide
AI Safety Research: From Lab Evals to Geopolitical Flashpoint
Related events (8)
NSA lost access to Anthropic's Mythos tool amid dispute with the company
The NSA lost access to an Anthropic AI tool called Mythos following a dispute between the agency and Anthropic, according to a New York Times report. The incident suggests friction between a major AI safety-focused lab and a U.S. intelligence agency over terms or conditions of use. This is notable as a signal of how frontier AI labs are navigating government and national security relationships.
MIT Tech Review: Three things to watch in Anthropic's feud with the US government
MIT Technology Review covers an ongoing dispute between Anthropic and the US government, centered on an AI model called Mythos that Anthropic reportedly built. The piece identifies three key developments to monitor as the conflict unfolds. The item signals a significant regulatory or policy confrontation involving a major frontier AI lab.
The AI Ad-Hoc Prior Restraint Era Begins
Zvi Mowshowitz reports that the White House has ordered Anthropic to halt expansion of access to Mythos, and is considering a broader policy shift to a prior restraint regime requiring government approval before releasing highly capable AI models. This would represent a major reversal of current U.S. frontier AI policy. The commentary analyzes the implications of such a regulatory posture for the AI industry.
GPT-5.6 launches in gated release; U.S. government restricts frontier AI model access
OpenAI announced GPT-5.6 in three tiers (Sol, Terra, Luna) but restricted early access to government-vetted partners at the Trump administration's request, framing the move as temporary while expressing frustration with the emerging involuntary licensing regime. Separately, the U.S. Commerce Department partially lifted a two-week export block on Anthropic's Claude Mythos 5, clearing access for 100+ trusted U.S. institutions while maintaining broader export controls. The episode establishes a new regulatory pattern in which Washington exerts direct control over frontier AI model releases, affecting both OpenAI and Anthropic. Additional items in the roundup cover Google integrating computer use into Gemini 3.5 Flash, Meta releasing Brain2Qwerty v2 for non-invasive brain-to-text decoding, and IBM's 0.7nm transistor design.
US government orders Anthropic to suspend access to Fable 5 and Mythos 5 citing national security jailbreak concerns
The US government issued an export control directive requiring Anthropic to immediately disable Fable 5 and Mythos 5 for all foreign nationals, effectively forcing a full customer suspension to ensure compliance. The government cited awareness of a jailbreak method, but Anthropic disputes the severity, stating the demonstrated technique is a narrow, non-universal jailbreak that produces results already achievable by other publicly available models including GPT-5.5. Anthropic is complying with the directive while publicly disagreeing with the standard applied, arguing that requiring perfect jailbreak resistance would halt all frontier model deployments industry-wide. This is a significant regulatory and safety governance flashpoint involving government authority over commercial AI model access.
U.S. Department of War bans Anthropic, contracts OpenAI for classified AI systems after standoff over safety restrictions
The U.S. Department of War designated Anthropic a supply-chain risk to national security after the company refused to remove restrictions on Claude's use for domestic surveillance and autonomous weapons, effectively banning it from military and contractor use. OpenAI signed a contract allowing use of its models 'for all lawful purposes' with ambiguous carve-outs for surveillance and autonomous weapons, which Altman later called rushed and renegotiated. The standoff culminated in a Trump Truth Social post threatening civil and criminal consequences against Anthropic, followed by Hegseth's formal designation. The episode marks a significant precedent: the supply-chain risk designation, previously applied only to foreign companies, was used against a U.S. AI lab over its own usage policies.
Anthropic publishes frontier model security recommendations including multi-party authorization and secure development frameworks
Anthropic released a policy and technical guidance document outlining cybersecurity best practices for securing frontier AI models, including multi-party authorization to AI-critical infrastructure, adoption of NIST SSDF and SLSA supply chain standards, and public-private cooperation modeled on critical infrastructure sectors. The post argues that advanced AI models warrant security levels far exceeding standard commercial practices and recommends government procurement requirements as a near-term enforcement mechanism. Anthropic states it is actively implementing these controls internally and calls on other labs and governments to adopt similar frameworks.
Anthropic awarded $200M DOD agreement to prototype frontier AI for national security
The U.S. Department of Defense's Chief Digital and Artificial Intelligence Office (CDAO) has awarded Anthropic a two-year, $200M ceiling prototype other transaction agreement to develop frontier AI capabilities for national security applications. Work will include fine-tuning models on DOD data, adversarial AI risk mitigation, and responsible AI adoption across the defense enterprise. Anthropic will leverage its Claude Gov models and existing partnerships with Palantir and AWS-hosted infrastructure. This is a significant expansion of Anthropic's federal footprint, building on prior deployments with defense and intelligence agencies.