Anthropic spent 31M output tokens on Riemann zeta search—the real signal is the architecture

Anthropic 用 31M output token 搜索黎曼猜想，真正的信号在搜索架构

Anthropic used an unreleased Claude to raise the proven lower bound of Riemann zeta zeros on the critical line from 41.6% to 67.2%—still far from proving the Riemann Hypothesis. The real story is the search architecture: two Claude Code sessions burned 31M output tokens. Round one produced 650 ideas, all failed, but left a ledger of 106 partial survivors with kill criteria. Round two coordinated ~60 subagents that rechecked the ledger and stitched a final route via stepping-stone transfers. The key insight was switching from requiring all-positive structure to counting usable positive directions. Lean formalization is sorry-free, but effective forms are missing from headline statements and independent third-party review is absent. Compared with GPT-5 on Erdős and OpenAI's ten math advances, the pattern is clear: generation and formalization are accelerating fast, while human understanding and absorption stay flat. The bottleneck is shifting from discovery to comprehension.

Why it matters: Anthropic used an unreleased model for math search — the 31M-token engineering details and hostile review mechanism are real signal, not pure PR. Docked slightly because pure math is far from product impact, and the post doesn't disclose the model name or token cost.