Guardian

Anthropic investigates report of rogue access to hack-enabling Mythos AI

BBC News

Claude Mythos AI unauthorised access claim probed by Anthropic

Financial Times

Anthropic investigating unauthorised access of powerful Mythos AI model

Bloomberg

Anthropic Mythos Model Is Being Accessed By Unauthorized Users

Anthropic

Project Glasswing: Securing critical software for the AI era

MarioNawfal

ChrisRMcGuire

The Register

Anthropic Mythos shaping up as nothingburger

RTE.ie

Powell warned bank CEOs on Anthropic model risks: sources

The Telegraph

Bank of England raises alarm over threat from AI ‘too dangerous to release’

Reuters

Japan's financial watchdog to meet top banks to discuss Mythos AI model

CTVNews

Canadian banks, regulators discussed Mythos AI, minister to meet with Anthropic

Metaculus

AI Unauthorized Access Before 2033?

Anthropic confirmed it is investigating a report of unauthorized access to its Claude Mythos Preview model through a third-party vendor environment. The company said it has no evidence the access extended beyond that vendor's systems.

Wall Street Journal

Anthropic confirmed it is investigating a report of unauthorized access to its Claude Mythos Preview model through a third-party vendor environment. The company said it has no evidence the access extended beyond that vendor's systems.

According to Bloomberg, a handful of users in a private online forum gained access to Mythos on the day Anthropic announced a limited release to companies including Apple, Amazon, Cisco and Goldman Sachs for testing purposes.

According to Bloomberg, a handful of users in a private online forum gained access to Mythos on the day Anthropic announced a limited release to companies including Apple, Amazon, Cisco and Goldman Sachs for testing purposes.

One person in the group had existing permissions as a contractor for Anthropic, which they used to access the model. The group also employed internet sleuthing tools commonly used by cybersecurity researchers to locate the model.

One person in the group had existing permissions as a contractor for Anthropic, which they used to access the model. The group also employed internet sleuthing tools commonly used by cybersecurity researchers to locate the model.

Anthropic developed Mythos Preview under its Project Glasswing initiative, restricting access to roughly 50 organizations maintaining critical infrastructure, including Amazon, Google, Microsoft and the Linux Foundation.

Anthropic developed Mythos Preview under its Project Glasswing initiative, restricting access to roughly 50 organizations maintaining critical infrastructure, including Amazon, Google, Microsoft and the Linux Foundation.

The UK's AI Security Institute assessed that Mythos was a step up from prior models in cyber threat capability, noting it could carry out multi-step attacks and discover IT system weaknesses without human intervention.

The UK's AI Security Institute assessed that Mythos was a step up from prior models in cyber threat capability, noting it could carry out multi-step attacks and discover IT system weaknesses without human intervention.

Anthropic committed $100 million in model usage credits to Project Glasswing and donated $4 million to open-source foundations, including Alpha-Omega, OpenSSF and the Apache Software Foundation, to help maintainers address emerging security risks.

Anthropic committed $100 million in model usage credits to Project Glasswing and donated $4 million to open-source foundations, including Alpha-Omega, OpenSSF and the Apache Software Foundation, to help maintainers address emerging security risks.

Guardian #

BBC News #

Financial Times #

Bloomberg #

Anthropic #

The Register #

RTE.ie #

The Telegraph #

Reuters #

CTVNews #

Metaculus #

Artificial Intelligence

Anthropic investigates report of rogue access to hack-enabling Mythos AI

Anthropic Probes Unauthorized Access to Claude Mythos AI

Anthropic investigatesProbes reportUnauthorized ofAccess rogue access to hack-enablingClaude Mythos AI

Go Deeper

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

Anthropic Probes Unauthorized Access to Claude Mythos AI

Anthropic investigatesProbes reportUnauthorized ofAccess rogue access to hack-enablingClaude Mythos AI

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