Politico

EU pressure builds on Anthropic over Mythos hacking risks

Europarl

How safe is AI? MEPs question experts on new risks and rules

Europes laws ill-equipped to deal with superhacking AI, lawmakers warn

Reuters

European Commission Is Contact With Anthropic Mythos Dombrovskis Says 2026 05 04

Bloomberg

Eu In Talks With Anthropic To Get Banks Tested For Mythos Flaws

Euro Finance Chiefs Want Mythos Ai Access To Prepare Defenses

Mezha

EU in talks with Anthropic to use Mythos model to check banks for vulnerabilities

Anadolu Agency

White House pushes back on Anthropics plan to broaden Mythos AI model access: Report

The Wall Street Journal

White House Opposes Anthropics Plan To Expand Access To Mythos Model Dc281Ab5

European Conservative

EU Locked Out of AI That Could Stop Cyber Attacks

Bankinfosecurity

European Meps Push For Stronger Post Mythos Cybersecurity A 31599

Anthropic

Project Glasswing: Securing critical software for the AI era

Claude Mythos Preview \ red.anthropic.com

Thirty members of the European Parliament from six political groups on Monday wrote to Commission Executive Vice President Henna Virkkunen calling for a "European mitigation plan" to address hacking risks and urging that EU cyber agency ENISA be granted access to Anthropic's Mythos AI system.

Thirty members of the European Parliament from six political groups on Monday wrote to Commission Executive Vice President Henna Virkkunen calling for a "European mitigation plan" to address hacking risks and urging that EU cyber agency ENISA be granted access to Anthropic's Mythos AI system.

Anthropic announced in early April that its Mythos AI system outperformed most humans in identifying and exploiting software vulnerabilities, prompting the company to restrict access to a small group of mostly U.S.-based organizations over misuse concerns via Project Glasswing.

Anthropic announced in early April that its Mythos AI system outperformed most humans in identifying and exploiting software vulnerabilities, prompting the company to restrict access to a small group of mostly U.S.-based organizations over misuse concerns via Project Glasswing.

Nearly a month after Mythos was announced, no European banks had been granted access to the model, while cybersecurity experts warned it could accelerate attacks on banks' technology systems.

Nearly a month after Mythos was announced, no European banks had been granted access to the model, while cybersecurity experts warned it could accelerate attacks on banks' technology systems.

European Economic Commissioner Valdis Dombrovskis confirmed the European Commission had been briefed by Anthropic on Mythos's cyber capabilities and risks, and said the EU was in talks to allow European companies and banks to conduct cyber resilience testing using the model.

European Economic Commissioner Valdis Dombrovskis confirmed the European Commission had been briefed by Anthropic on Mythos's cyber capabilities and risks, and said the EU was in talks to allow European companies and banks to conduct cyber resilience testing using the model.

Spain's economy minister Carlos Cuerpo called for the EU to use regulatory tools such as the AI Act to guarantee access to Mythos, warning the model could find vulnerabilities "across all sectors."

Spain's economy minister Carlos Cuerpo called for the EU to use regulatory tools such as the AI Act to guarantee access to Mythos, warning the model could find vulnerabilities "across all sectors."

On Wednesday, officials from the European Commission and ENISA appeared before the European Parliament to discuss Mythos-related risks. Anthropic declined to attend, citing "short notice," a decision Dutch lawmaker Kim van Sparrentak called "extremely worrying."

On Wednesday, officials from the European Commission and ENISA appeared before the European Parliament to discuss Mythos-related risks. Anthropic declined to attend, citing "short notice," a decision Dutch lawmaker Kim van Sparrentak called "extremely worrying."

Politico #

Europarl #

Reuters #

Bloomberg #

Mezha #

Anadolu Agency #

The Wall Street Journal #

European Conservative #

Bankinfosecurity #

Anthropic #

Anthropic's refusal to share Mythos with European regulators is a serious threat to global cybersecurity governance. A model capable of outperforming most humans at finding software vulnerabilities cannot be left in the hands of a small circle of mostly American organizations while European banks and institutions are left defenseless. Regulatory access isn't a bureaucratic demand, it's a basic requirement for responsible AI deployment.

Anthropic's refusal to share Mythos with European regulators is a serious threat to global cybersecurity governance. A model capable of outperforming most humans at finding software vulnerabilities cannot be left in the hands of a small circle of mostly American organizations while European banks and institutions are left defenseless. Regulatory access isn't a bureaucratic demand, it's a basic requirement for responsible AI deployment.

Europe's Mythos problem is self-inflicted, as years of prioritizing AI regulation over AI development left the continent without the tools to secure its own infrastructure. While American firms like Amazon, Google and JPMorgan Chase gained access to a system that uncovered 271 Firefox flaws alone, Brussels was busy writing rulebooks. Demanding access now doesn't fix the deeper failure of choosing compliance over capability.

Europe's Mythos problem is self-inflicted, as years of prioritizing AI regulation over AI development left the continent without the tools to secure its own infrastructure. While American firms like Amazon, Google and JPMorgan Chase gained access to a system that uncovered 271 Firefox flaws alone, Brussels was busy writing rulebooks. Demanding access now doesn't fix the deeper failure of choosing compliance over capability.

The AI Doc: Or How I Became an Apocaloptimist

If Anyone Builds It, Everyone Dies

Artificial Intelligence

Wiktor Dabkowski/Bloomberg/Getty Images

Wiktor Dabkowski/Bloomberg/Getty Images

EU Pushes for Access to Anthropic's Mythos AI

Computer security

Europe

Politics

Europe is being left dangerously exposed because Anthropic won't share Mythos with EU regulators or European banks, even as the model can find vulnerabilities in every major operating system. Skipping a European Parliament hearing only deepens the concern that a handful of mostly American organizations get to decide who stays safe. The EU's AI Act enforcement powers kick in August 2026, and regulators are right to demand access before a crisis hits.

Europe is being left dangerously exposed because Anthropic won't share Mythos with EU regulators or European banks, even as the model can find vulnerabilities in every major operating system. Skipping a European Parliament hearing only deepens the concern that a handful of mostly American organizations get to decide who stays safe. The EU's AI Act enforcement powers kick in August 2026, and regulators are right to demand access before a crisis hits.

Expanding Mythos access isn't a matter of fairness — it's a genuine national security risk, and the White House is right to pump the brakes. Anthropic itself warned the model found thousands of high-severity vulnerabilities across every major platform, and adding 70 more organizations strains the computing capacity needed to keep government access effective. Rushing broader rollout before safeguards are solid is exactly how catastrophic cyberattacks happen.

Expanding Mythos access isn't a matter of fairness — it's a genuine national security risk, and the White House is right to pump the brakes. Anthropic itself warned the model found thousands of high-severity vulnerabilities across every major platform, and adding 70 more organizations strains the computing capacity needed to keep government access effective. Rushing broader rollout before safeguards are solid is exactly how catastrophic cyberattacks happen.

EU Pushes for Access to Anthropic's Mythos AI

EU Pushes for Access to Anthropic's Mythos AI

The Spin

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

EU Pushes for Access to Anthropic's Mythos AI

EU Pushes for Access to Anthropic's Mythos AI

The Spin

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters