7 papers
Interaction Creates Dynamical AI Behavior Absent in Isolation
Bella Xinrui Li, Frank Yingjie Huo, Neil F Johnson
What will happen when AI agents interact in daily life, e.g. when one AI starts bossing another around? We find a counterintuitive answer that opens new avenues for out-of-equilibr…
Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs
Neil F. Johnson, Frank Yingjie Huo, Bella Xinrui Li
Increasing the temperature of an ordinary many-state system increases access to a wider range of states and hence increases its entropy. We find the opposite in ChatGPT-like AIs, e…
Many-body Tipping Dynamics of ChatGPT-like AIs
Frank Yingjie Huo, Neil F. Johnson
Why do ChatGPT-like AIs, despite major architectural and training differences, unexpectedly tip to undesirable content (e.g. harmful, misleading, repetitive) even under determinist…
Multispin Physics of AI Tipping Points and Hallucinations
Neil F. Johnson, Frank Yingjie Huo
Output from generative AI such as ChatGPT, can be repetitive and biased. But more worrying is that this output can mysteriously tip mid-response from good (correct) to bad (mislead…
Jekyll-and-Hyde Tipping Point in an AI's Behavior
Neil F. Johnson, Frank Yingjie Huo
Trust in AI is undermined by the fact that there is no science that predicts -- or that can explain to the public -- when an LLM's output (e.g. ChatGPT) is likely to tip mid-respon…
Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond
Frank Yingjie Huo, Neil F. Johnson
We derive a first-principles physics theory of the AI engine at the heart of LLMs' 'magic' (e.g. ChatGPT, Claude): the basic Attention head. The theory allows a quantitative analys…