NeFut Logo NeFut
Admin Login

[CS.AI] Unveiling Many-body Tipping Dynamics in ChatGPT-like AIs

Published at: 2026-07-30 22:00 Last updated: 2026-07-30 23:39
#AI #Machine Learning #optimization

Abstract

Why do ChatGPT-like AIs, despite major architectural and training differences, unexpectedly tip to undesirable content (e.g. harmful, misleading, repetitive) even under deterministic greedy decoding?

We show that a broad class of such tippings is caused by the many-body interactions between tokens (spins) as they cross the finite-layer system. Tipping emerges as a dynamical first passage process between competing output basins. Attention disorder controls the transport toward, away from, or along the basins' boundary. A few-basin reduction yields a closed finite-layer threshold, whose coarse-grained predictions show good agreement across ChatGPT-like families.

These results suggest that a broad class of AI failures represents 'foreseeable engineering risk' rather than inherently unpredictable behavior, with important implications for legal and societal assessments of AI harm.

Blogger's Review: This study delves into the instability of content generation in ChatGPT-like AIs, revealing the core role of many-body interactions in the generation process. Understanding these mechanisms not only aids in improving AI model design but also provides a crucial perspective for assessing the potential risks posed by AI technologies. By viewing these issues as foreseeable engineering risks, society can more effectively address the challenges brought by AI.

Original Source: https://arxiv.org/abs/2607.25279

[h] Back to Home