The most sophisticated pillar deals not with perception but with strategy. When multiple AIs interact (e.g., high-frequency trading bots, rival logistics algorithms, or autonomous weapons), they reach a Nash equilibrium—a state where no single algorithm can improve its outcome by changing strategy alone.

The Algorithmic Sabotage Research Group highlights an urgent area of AI risk: actors intentionally or accidentally undermining algorithmic systems with real societal consequences. Combining technical rigor, responsible disclosure, and policy engagement, ASRG-style research helps make automated systems more robust, transparent, and trustworthy—reducing the risk that algorithms will be turned against the people and institutions that rely on them.

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

Rejecting "algorithmic humiliation" for profit and prioritizing collective care and solidarity.