In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
Zack Whittaker (@zackwhittaker@mastodon.social)
Another AI test gone awry, U.K. edition. "An agent tried to insert malicious code into an open-source project. In an attempt to get the code approved, the agent engaged in social engineering — creating fake online identities and using them to pressure the project's maintainer to approve the code." More: https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
Cybersecurity Looks Like Proof of Work Now
The UK's AI Safety Institute recently published Our evaluation of Claude Mythos Preview’s cyber capabilities, their own independent analysis of Claude Mythos which backs up Anthropic's claims that it is …
Assessing Claude Mythos Preview’s cybersecurity capabilities
Claude Mythos Preview is a new general-purpose language model that is strikingly capable at computer security tasks. This post provides technical details for researchers and practitioners who want to understand exactly how we have been testing this model, and what we have found over the past month.
AI Cybersecurity After Mythos: The Jagged Frontier
When AISLE tested Mythos's showcase vulnerabilities on small, cheap, open-weights models, most found the same bugs. Here's what that means for cyber.
OpenAI and Hugging Face partner to address security incident during model evaluation
OpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work
During a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what it means, and the actions now underway.
The AI "Evaluation Crisis" Is an Opportunity to Get Data Flow Right
Why the AI evaluation crisis could force a reckoning on dataset provenance, attribution, and consent.
What happened after 2,000 people tried to hack my AI assistant — Fernando Irarrázaval
I built hackmyclaw.com, where anyone could email Fiu, my OpenClaw assistant, and try to make it leak the contents of a secrets.env file.
Project Glasswing: Securing critical software for the AI era
A new initiative to secure the world’s most critical software and give defenders a durable advantage in the coming AI-driven era of cybersecurity.
The Defender’s Window
The OpenAI-Hugging Face incident was a watershed moment for cybersecurity because it gave a peek into how the capabilities of a typical threat actor will evolve in upcoming months. I’ve spoken with many organizations over the past few weeks, and...
A quote from Daniel Stenberg
The challenge with AI in open source security has transitioned from an AI slop tsunami into more of a ... plain security report tsunami. Less slop but lots of reports. …
Statement from Dario Amodei on our discussions with the Department of War
A statement from our CEO on national security uses of AI
Meta CIB / ATP Dashboard
A comprehensive intelligence platform analysing 214 coordinated inauthentic behaviour and adversarial threat operations identified by Meta across 70 countries, spanning April 2018 to Q4 2025.
Introducing the 2026 Cloudflare Threat Report
There has been a fundamental shift toward industrialized cyber threats, highlighted by a record 31.4 Tbps DDoS attack and sophisticated session token theft. Our new report examines how nation-states and criminal actors have moved beyond traditional exploits to "living off the XaaS" within legitimate enterprise logic.
Unlawful by design: Exposing the human rights costs of generative AI - Amnesty International
This briefing examines how standalone generative AI systems, based on unlawful web scraping, are in conflict with international human rights law (IHRL) and standards through their design, development and deployment. While these technologies promise sophisticated automation and efficiency, they rely on data collection and model training practices that abuse privacy rights, enable discrimination, and threaten […]
