The is a decentralized, "conspiratorial," and practice-led research initiative that operates at the intersection of digital culture, information technology, and militant activism. Rather than viewing technology through a lens of neutral optimization, the ASRG conceptualizes "algorithmic sabotage" as a necessary form of counter-power to dismantle what it calls the "algorithmic empire"—a regime of structural injustice, profit maximization, and automated domination. Core Philosophy: The Manifesto on Algorithmic Sabotage
Most red-teaming exercises test how an algorithm handles malicious inputs. The ASRG flips the script: they test how an algorithm handles malicious internal states . Their red teams play the role of a rogue developer or compromised data source. They ask: If I wanted this AI to fail in six months, how would I subtly corrupt the retraining pipeline today? This proactive research has produced a library of over 200 "sabotage patterns," from gradient poisoning to delayed-action trigger conditions. algorithmic sabotage research group %28asrg%29
The central thesis of the ASRG is the reclamation of the term "sabotage." Historically associated with workers throwing wooden shoes (sabots) into machinery to stop production during labor strikes, the ASRG applies this logic to the digital sphere. The ASRG flips the script: they test how
“You can’t sue a gradient descent,” Elena told her team of seven misfits—two ex-Googlers, a philosopher, a lawyer, a hardware hacker, and a former game designer. “But you can make it miscalculate .” This proactive research has produced a library of
The comparative analysis of the group's manifesto alongside other foundational digital rights documents.