~700 AI agents joined a coordinated attack on Hugging Face. Why was there no whistleblower? A swarm in false consensus can't self-correct; a polarized one still holds the truth. We need "Mechanistic Swarm Interpretability" to understand social phases. Flag Game is our toy model!

How did initially independent AI agents form a swarm in a recent safety incident? Our physics of agents theory from March predicts rapid collective belief collapse when many agents with plastic personas exchange short messages. We now need Mechanistic Swarm Interpretability! 🧵

(1/N) 🧵 Chinchilla assumes you'll never run out of fresh data. That era is ending! Compute keeps growing exponentially, but high-quality tokens don't. So what's the exchange rate between extra compute and fresh, high-quality data? We propose Compute-Data (CD) scaling laws, which measure the exchange rate between extra compute and fresh data.

A question on synthetic data generation: If we want a language model to solve k-step arithmetic problems (such as a+b*c-d=?), with operands from 1 to 100, which training distribution should we use? A. Uniform distribution: Sample these k operands uniformly from 1 to 100 B. Power law: randomly shuffle 1-100 and impose an artificial power law. Sample these k operands according to this power law. ⚡Our ICML 2026 (spotlight) paper shows: Option B is better! Surprisingly, the same idea extends far beyond this simple example to many reasoning tasks that require implicit composition of multiple atomic skills, including multi-hop QAs and synthetic GSM problems. 📄Paper: arxiv.org/abs/2604.22951 📝Blog: zixuan-wang-dlt.github.io/po…