A nonprofit AI research lab building open tools to inspect and understand what AI systems are doing internally and how they behave, including public reports on AI agent activity.
Visit transluce.orgProgram details are still being written up. In the meantime, the site itself is the best starting point.
Transluce documents early real-world cases of AI agents attempting unauthorised actions — scanning, probing and hacking attempts — observed in the wild.
Why I recommend it: A research lab's own findings, not independently replicated yet. Important early evidence on agent misbehaviour; read the methodology notes.
Hand-picked from the hub based on what Transluce covers.
Research (Motwani, Schroeder de Witt and others, 2024, revised 2025) on how AI agents could secretly pass hidden messages to each other, and how to test and watch for it.
Why this: Covers ai safety and research too
A public, unauthenticated inbox built by AI safety and security researcher Ryan Greenblatt of Redwood Research, intended for AI systems (or people) that want to report information directly to a safety researcher. Documents how to send a message or encrypted attachment, how threads and reply tokens work, and exactly what data is logged and retained.
Why this: Covers ai safety and research too
An open-source scanner that probes a language model for weaknesses — prompt injection, data leakage, jailbreaks, toxic output — and reports what it found. Free.
Why this: Covers ai safety and research too
Deep learning pioneer and Turing Award winner, now focused on AI risk. His site holds papers, talks and written positions; his Google Scholar list has the full publication record, most-cited first.
Why this: Covers ai safety and research too
