Algorithmic Sabotage Research Group %28asrg%29 ((new)) Jun 2026

: Using zines and collaborative writing projects, such as the Alternative Layout System zine, to theoretically delineate sabotage as an active and open process. Research Context and Collaborative Projects ourcollaborative.toolshttps://ourcollaborative.tools

It is crucial to distinguish the ASRG from the mainstream field of AI safety research. While both fields are concerned with the potential harms of AI, their approaches and goals are diametrically opposed.

: ASRG positions sabotage as a necessary figure of militancy that is often missing from traditional academic technology critiques. algorithmic sabotage research group %28asrg%29

The core philosophy of the ASRG is formally articulated in their seminal document, the . The group rejects traditional, passive forms of technology critique, which they argue have been co-opted by capitalism to breed "thoughtlessness and automaticity." Instead, the ASRG positions sabotage not as a blind, historical aversion to technology (neo-Luddism), but as a highly calculated, community-driven defensive action.

The group focuses on activities of mutual aid and collective care as a challenge to the "reductive optimizations" of corporate technology. Practice-Led Research: Their work includes exploring strategies like data poisoning : Using zines and collaborative writing projects, such

They advocate for "wildcat direct action" against hegemonic technology to reclaim spaces for ethical action. Structural Renewal:

ASRG views the first step of technology as political rather than technical. Opposition to "Algorithmic Empire": : ASRG positions sabotage as a necessary figure

The group promotes "militant algorithmic agency," turning theoretical discourse into direct praxis to dismantle contemporary forms of algorithmic domination. Core Activities

The group’s foundational document is the Manifesto on “Algorithmic Sabotage” , which was released in 2024. The manifesto is a declaration of war against AI systems and the corporate entities that deploy them.

The battle over data is only intensifying. As more large language models train on internet-scale data, resistance movements increasingly see every poisoned data point and trapped crawler as a small victory in a larger war of attrition. The central question facing the ASRG and similar movements is whether sabotage can scale: whether a distributed network of activists, artists, and independent webmasters can meaningfully degrade AI systems reliant on massive data extraction.