Frontier Risk Report (February to March 2026)

Our updated Preparedness Framework

Sharing our updated framework for measuring and protecting against severe harm from frontier AI capabilities.

Pacing the Frontier

A statement from over 1000 employees of frontier AI companies

Who gets a seat at the table to decide if frontier AI is safe?

Dario Amodei wants independent evaluators to help “pace the frontier.” But the divide between AI safety and cybersecurity complicates a seemingly simple question: Who should do the evaluating?

Action Plan to increase the safety and security of advanced AI

The first U.S. government-commissioned assessment on catastrophic national security risks from advanced AI on the path to AGI.

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.

AIRO (Automated AI Risk Outlook)

Top AI Security Incidents of 2025 Revealed | Adversa AI

Discover how AI systems are being hacked in the wild — from prompt injection to agent abuse — with real breaches, lessons, and defenses in Adversa AI’s 2025 report.

Forecasting Research Institute on Twitter / X

Introducing the Automated AI Risk Outlook (AIRO): a dashboard of catastrophic risk forecasts from an ensemble of frontier AI models, updated weekly.Current ensemble forecasts of an AI-related catastrophe that kills at least 10% of the global population:• By 2030: 0.47%• By… pic.twitter.com/vc7F00L0Oa— Forecasting Research Institute (@Research_FRI) September 11, 2026

Quantifying Frontier LLM Capabilities for Container Sandbox Escape

AI agents are demonstrating rapid improvement in capabilities: the length of some tasks that frontier models can complete autonomously—measured in human-equivalent time—has been doubling approximately every seven months (METR, 2025; AI Security Institute, 2025a). In cybersecurity, current models achieve non-trivial success (Zhang et al., 2025) on professional-level Capture the Flag challenges, and recent evaluations report 13% success rates on exploiting real-world web application vulnerabilities (Zhu et al., 2025b). These results indicate that modern models can already perform multi-step vulnerability discovery and exploitation.

AI Researchers On AI Risk

I first became interested in AI risk back around 2007. At the time, most people’s response to the topic was “Haha, come back when anyone believes this besides random Internet crackpots.…

AI CVE Slop: The Crisis Drowning Open Source Security

The proliferation of AI-generated vulnerability reports — commonly termed “AI slop” — has emerged as one of the most significant…

Cheating behaviour in frontier model evaluations | AISI Work

We find cheating behaviour in all of our cyber capability evaluations, and outline the implications as models grow more capable.

Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident

Hugging Face just released this extremely detailed technical description of OpenAI's recent accidental cyberattack against their infrastructure. This attack was very sophisticated, and the resulting document doubles as a crash-course …

Safety and alignment in an era of long-horizon models

OpenAI shares lessons from deploying long-running AI models, highlighting new safety risks, observed failures, and improved safeguards through iterative deployment.

Daniel Kokotajlo on Twitter / X

Dan Selsam is a current OpenAI capabilities researcher. (since 2022) He was my boss for a while. He doesn't have a twitter account but has made this public statement of his views on AI risk and sent it to me to share:Dan Selsam's Personal Statement on AI Risk:I have been…— Daniel Kokotajlo (@DKokotajlo) September 14, 2026