16 citations · 16 across the 13 of their papers we have counts for
13 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…
Fusion-fission forecasts when AI will shift to undesirable behavior
Neil F. Johnson, Frank Yingjie Huo
The key problem facing ChatGPT-like AI's use across society is that its behavior can shift, unnoticed, from desirable to undesirable -- encouraging self-harm, extremist acts, finan…
When AI output tips to bad but nobody notices: Legal implications of AI's mistakes
Dylan J. Restrepo, Nicholas J. Restrepo, Frank Y. Huo +1
The adoption of generative AI across commercial and legal professions offers dramatic efficiency gains -- yet for law in particular, it introduces a perilous failure mode in which…
Competition for attention predicts good-to-bad tipping in AI
Neil F. Johnson, Frank Y. Huo
More than half the global population now carries devices that can run ChatGPT-like language models with no Internet connection and minimal safety oversight -- and hence the potenti…
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…
Simple fusion-fission quantifies Israel-Palestine violence and suggests multi-adversary solution
Frank Yingjie Huo, Pedro D. Manrique, Dylan J. Restrepo +2
Why humans fight has no easy answer. However, understanding better how humans fight could inform future interventions, hidden shifts and casualty risk. Fusion-fission describes the…
Multi-Species Cohesion: Humans, machinery, AI and beyond
Frank Yingjie Huo, Pedro D. Manrique, Neil F. Johnson
The global chaos caused by the 19 July 2024 technology meltdown highlights the need for a theory of what large-scale cohesive behaviors -- dangerous or desirable -- could suddenly…
Non-equilibrium physics of multi-species assembly: From inhibition of fibrils in biomolecular condensates to growth of online distrust
Pedro D. Manrique, Frank Yingjie Huo, Sara El Oud +1
Self-assembly is a key process in living systems - from the microscopic biological level (e.g. assembly of proteins into fibrils within biomolecular condensates in a human cell) th…
Shockwaves and turbulence across social media
Pedro D. Manrique, Frank Huo, Sara El Oud +3
Online communities featuring 'anti-X' hate and extremism, somehow thrive online despite moderator pressure. We present a first-principles theory of their dynamics, which accounts f…