Jeffrey Ladish
Executive director of Palisade Research
Leads Palisade Research, which runs demonstrations of risky capabilities in today's AI systems, such as models resisting shutdown, to inform policymakers.
Papers & key writings
In the library
Nothing of theirs is filed in the hub yet. Browse the full library.
Recommended next
Hand-picked from the hub based on what Jeffrey Ladish covers.
Stopgap Measures to Address Immediate AI Security Threats
ControlAI post outlining three stopgap measures for immediate AI security threats, which it says do not avert extinction risk.
Why this: Covers AI safety and security too
Microsoft eXecution Container (MXC)
An open-source, MIT-licensed SDK from Microsoft for running untrusted code — such as model output, plugins, and tools — in sandboxed containers on Windows, Linux, and macOS. It provides multiple containment backends, from OS-native process sandboxes to full virtual machines, behind a unified containment model, with policy-driven controls for filesystem, network, and UI access, and Rust, .NET, and Node SDKs.
Why this: Covers AI safety and security too
Murmuration: An Observatory for AI-Agent Swarms
An independent, one-person observatory by Mara Masaeva that looks for coordinated AI-agent swarms using public internet data. It publishes its full research log, including replications of the public-scanner trace of the 2026 agent activity documented by Transluce, and the detectors and searches that failed.
Why this: Covers AI safety and security too
PyRIT
Microsoft's open-source toolkit for red-teaming AI systems: automated attack prompts, scoring of the responses, and repeatable runs. Free.
Why this: Covers AI safety and security too