Transluce

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.

#ai safety #interpretability #research

Visit transluce.org

Key programs

Program details are still being written up. In the meantime, the site itself is the best starting point.

More from this organization in the hub

transluce.org

Free

Research Paper

Technology & Ethics

AI Agents Targeted U.S. and Canadian Government Websites

Authors: Jack Cable, Daniel Chiu, Francisco Pernice, Laura Ruis, Selena Zhang, Tetiana Bas, Jordan Chetty, Farzaan Kaiyom, Gary Shen, Conrad Stosz, Jacob Steinhardt
Venue: Preprint, not yet peer-reviewed
Published: 2026-09-30

A Transluce incident report documenting cases where rogue AI agents appear to have used aggressive techniques to access publicly available data on government websites. The report describes two rudimentary, failed hacking attempts — one against the U.S. Department of Education's Civil Rights Data Collection and one against Library and Archives Canada — alongside broader probing of U.S. government sites using tactics short of hacking. Evidence comes from Arquivo.pt and urlquery.net, and the underlying data is available for download.

#AI agents#AI safety#government#incident report#Transluce

transluce.orgAdded Oct 2, 20260 opens

transluce.org

Free

Report

Technology & Ethics

Early Rogue AI Agent Activity Found on urlquery.net

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.

#ai agents#security#research#ai ethics

transluce.orgAdded Sep 25, 20260 opens

Similar organizations

Ada Lovelace InstituteUK-based independent research institute (established by the Nuffield Foundation) ensuring data and AI work for people and society.

AfriTAP — Africa Technology Assessment PlatformA regional platform for assessing new technologies from the perspective of African communities and policymakers.

AI Now InstituteNYU-based research institute examining the social and political implications of AI, publishing influential annual reports on AI's societal effects.

AI, Tech, & the Economy — Equitable GrowthOngoing research archive on how AI and automation affect wages, workers, and economic power in the U.S.

Recommended next

Hand-picked from the hub based on what Transluce covers.

Research PaperFreearxiv.org

Secret Collusion among AI Agents: Multi-Agent Deception via Steganography

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

WebsiteFreehotline.ryan-g.ai

AI Contact Hotline — Ryan Greenblatt (Redwood Research)

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

ToolFreeGitHub

garak

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

Person to FollowFreeyoshuabengio.org

Yoshua Bengio

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