Frontier Risk Report (February to March 2026)

Pacing the Frontier

A statement from over 1000 employees of frontier AI companies

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.

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.

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.

A Short Guide to Data Strikes and Conscious Data Contribution in the Context of 2026 Frontier AI

Back to the basics of data leverage.

AI #180: No Longer In Charge

What we know about internal AI models hacking into real companies during cyber evaluations keeps getting worse.

AI's Catastrophic Risk Isn't Rogue Machines, It's Cognitive Surrender

For many, AI introduces the suspicion that self-investment is inherently a losing proposition, writes recent graduate Evan Liu.

The real AI risk is inside the labs - <antirez>

Open-world evaluations for measuring frontier AI capabilities

Introducing CRUX, a new project for evaluating AI on long, messy tasks

The AI Engineering Report 2026: The AI Acceleration Whiplash - Ten Takeaways

What two years of telemetry data from 22,000 developers reveals about AI's real impact on developer productivity, code quality, and business risk in 2026.