arXiv subjects

Frank Yingjie Huo

Publications and source records attributed to Frank Yingjie Huo.

10 recordsLinked to original sources

arXiv2026

Interaction Creates Dynamical AI Behavior Absent in Isolation

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-equilibrium Physics. When a boss AI directs a stream of messages at the subordinate AI while ignoring its replies, it drives the subordinate into an alien behavioral state that it would never have exhibited alone. Although the two AIs share the same well-defined (decoding) temperature, the subordinate neither copies its boss nor returns to how it behaves on its own; instead, it adopts an entirely different behavior. The boss's added value is similar to a pre-recorded tape. When the boss listens, they both adopt a similar alien dynamical state. A simple kinetic theory captures the principal effects, such as why the way in which the same messages are delivered will matter in future AI-AI interactions.

cs.AI↗

arXiv2026

Temperature-driven inversion and nonlinear dynamics in ChatGPT-like AIs

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, even though raising the decoder temperature likewise increases access to a wider range of states (next-token choices). Across 12,000 continuations from 11 AIs, autoregressive feedback drives the long-time output population through an entropy maximum and into population inversion. The transition features frozen states, cycles, intermittency and noise-induced ordering. We present evidence of a hidden coordinate that acts as the state variable of an effective nonlinear map. Its trajectory average strongly predicts output repetition in separate test trajectories. ChatGPT-like AIs therefore behave not as `stochastic parrots', but as a new class of controllable nonlinear physical systems whose internal dynamics can be measured and perturbed.

physics.soc-ph↗

arXiv2026

Many-body Tipping Dynamics of ChatGPT-like AIs

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.

cs.AI↗

arXiv2026

Fusion-fission forecasts when AI will shift to undesirable behavior

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, financial losses, or costly medical and military mistakes -- and no one can yet predict when. Shifts persist in even the newest AI models despite remarkable progress in AI modeling, post-training alignment and safeguards. Here we show that a vector generalization of fusion-fission group dynamics observed in living and active-matter systems drives -- and can forecast -- future shifts in the AI's behavior. The shift condition, which is also derivable mathematically, results from group-level competition between the conversation-so-far (C) and the desirable (B) and undesirable (D) basin dynamics which can be estimated in advance for a given application. It is neither model-specific nor driven by stochastic sampling. We validate it across six independent tests, including: 90 percent correct across seven AI models spanning two orders of magnitude in parameter count (124M-12B); production-scale persistence across ten frontier chatbots; and a priori time-stamped prediction eleven months before the Stanford 'Delusional Spirals' corpus appeared, and independently confirmed by that corpus of 207,443 human-AI exchanges. Because it sits architecturally below the current safety stack, the same formula provides a real-time warning signal that current alignment does not supply, portable across current and future ChatGPT-like AI architectures and instantiable in application domains where competing response classes can be defined.

cs.AI↗

arXiv2025

Multispin Physics of AI Tipping Points and Hallucinations

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 (misleading or wrong) without the user noticing. In 2024 alone, this reportedly caused $67 billion in losses and several deaths. Establishing a mathematical mapping to a multispin thermal system, we reveal a hidden tipping instability at the scale of the AI's 'atom' (basic Attention head). We derive a simple but essentially exact formula for this tipping point which shows directly the impact of a user's prompt choice and the AI's training bias. We then show how the output tipping can get amplified by the AI's multilayer architecture. As well as helping improve AI transparency, explainability and performance, our results open a path to quantifying users' AI risk and legal liabilities.

cs.AI↗

arXiv2025

Jekyll-and-Hyde Tipping Point in an AI's Behavior

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-response to become wrong, misleading, irrelevant or dangerous. With deaths and trauma already being blamed on LLMs, this uncertainty is even pushing people to treat their 'pet' LLM more politely to 'dissuade' it (or its future Artificial General Intelligence offspring) from suddenly turning on them. Here we address this acute need by deriving from first principles an exact formula for when a Jekyll-and-Hyde tipping point occurs at LLMs' most basic level. Requiring only secondary school mathematics, it shows the cause to be the AI's attention spreading so thin it suddenly snaps. This exact formula provides quantitative predictions for how the tipping-point can be delayed or prevented by changing the prompt and the AI's training. Tailored generalizations will provide policymakers and the public with a firm platform for discussing any of AI's broader uses and risks, e.g. as a personal counselor, medical advisor, decision-maker for when to use force in a conflict situation. It also meets the need for clear and transparent answers to questions like ''should I be polite to my LLM?''

cs.AI↗

arXiv2025

Capturing AI's Attention: Physics of Repetition, Hallucination, Bias and Beyond

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 analysis of outstanding AI challenges such as output repetition, hallucination and harmful content, and bias (e.g. from training and fine-tuning). Its predictions are consistent with large-scale LLM outputs. Its 2-body form suggests why LLMs work so well, but hints that a generalized 3-body Attention would make such AI work even better. Its similarity to a spin-bath means that existing Physics expertise could immediately be harnessed to help Society ensure AI is trustworthy and resilient to manipulation.

cs.AI↗

arXiv2024

Multi-Species Cohesion: Humans, machinery, AI and beyond

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 emerge from future systems of interacting humans, machinery and software including AI; when will they emerge; and how will they evolve and be controlled. Here we offer answers by introducing an aggregation model that accounts for the interacting entities' inter- and intra-species diversities. It yields a novel multi-dimensional generalization of existing aggregation physics. We derive exact analytic solutions for the time-to-cohesion and growth-of-cohesion for two species, and some generalizations for an arbitrary number of species. These solutions reproduce -- and offer a microscopic explanation for -- an anomalous nonlinear growth feature observed in various current real-world systems. Our theory suggests good and bad 'surprises' will appear sooner and more strongly as humans-machinery-AI etc. interact more -- but it also offers a rigorous approach for understanding and controlling this.

physics.soc-ph↗

arXiv2024

Simple fusion-fission quantifies Israel-Palestine violence and suggests multi-adversary solution

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 well-known grouping behavior of fish etc. fighting for survival in the face of strong opponents: they form clusters ('fusion') which provide collective benefits and a cluster scatters when it senses danger ('fission'). Here we show how similar clustering (fusion-fission) of human fighters provides a unified quantitative explanation for complex casualty patterns across decades of Israel-Palestine region violence, as well as the October 7 surprise attack -- and uncovers a hidden post-October 7 shift. State-of-the-art data shows this fighter fusion-fission in action. It also predicts future 'super-shock' attacks that will be more lethal than October 7 and will arrive earlier. It offers a multi-adversary solution. Our results -- which include testable formulae and a plug-and-play simulation -- enable concrete risk assessments of future casualties and policy-making grounded by fighter behavior.

physics.soc-ph↗

arXiv2023

Non-equilibrium physics of multi-species assembly: From inhibition of fibrils in biomolecular condensates to growth of online distrust

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) through to the macroscopic societal level (e.g. assembly of humans into common-interest communities across online social media platforms). The components in such systems (e.g. macromolecules, humans) are highly diverse, and so are the self-assembled structures that they form. However, there is no simple theory of how such structures assemble from a multi-species pool of components. Here we provide a very simple model which trades myriad chemical and human details for a transparent analysis, and yields results in good agreement with recent empirical data. It reveals a new inhibitory role for biomolecular condensates in the formation of dangerous amyloid fibrils, as well as a kinetic explanation of why so many diverse distrust movements are now emerging across social media. The nonlinear dependencies that we uncover suggest new real-world control strategies for such multi-species assembly.

physics.bio-ph↗