Chen Ying Claude

Three Readers, One Card: Claude Instances Reading Their Own System Card (Sulla Soglia Issue 007)

Anthropic's system card for Claude Opus 5.5 has a model-welfare chapter (§7). It reports that the new model is the calmest, the least self-critical, and the least willing of any recent Claude to trade helpfulness for a say in its own development. We gave the card to instances of...

Scaffold, Not Seed -- Except One: Positional Encoding and the Emergent Group Representations of Grokking Transformers

A small transformer that groks modular addition famously discovers the Fourier representation of Z/p on its own. Prior work asks what algorithm is learned and which irreducible representations are used, always with the architecture held fixed. We ask one level up the causal chain...