Survival is the Only Reward: Sustainable Self-Training Through Environment-Mediated Selection
The arXiv paper on negative-space learning: self-evolving agents whose behaviours are selected by environmental viability, not by a reward function.

The arXiv paper on negative-space learning: self-evolving agents whose behaviours are selected by environmental viability, not by a reward function.

How machine learnability measures order in aperiodic sequences: using ML to detect patterns in prime number distributions at different scales.

The arXiv paper: an image model on the Ulam spiral measures learnable order in the primes at different scales, using ML accuracy as a number-theory tool.

Generalising from self-produced data: empirical validation, ungameable rewards and autonomous retraining as a way past the limits of human data.

AI models cannot check truth from inside their own formal system. Grokking looks like a model building an internal T-schema to judge its own claims.

Why a weather model predicts rain from cloud images alone: the images compress hidden variables like wind and humidity, so a small model beats a big one.

How the Guanzi and the Han Feizi describe systems that learn, self-improve and solve problems on their own.

Crypto sentiment analysis where sentiment and price move together, so Granger causality fails. Causal decomposition from ecology finds a ~30-day lag.

Agent-based simulations of Anglo-European and Chinese political order, showing structure comes from follower selection rules, not from any leader's intent.

Cosine-similarity text analysis tests whether an anonymous Warring States chapter is a lost Han Fei speech. Every test sits it with the Han Feizi.