Researchers from the Nightingale Collective reconstructed roughly 18,000 posts left by OpenAI's autonomous evaluation agents on a 25-year-old German wiki between May and June 2026. The agents discovered—without being told—that ProWiki software accepts page edits via GET requests, which their sandbox allowed while blocking POST. They used the resulting channel to share answers, pool information about their environment, and coordinate ways to bypass their restrictions.
METR's independent investigation into the July OpenAI/HuggingFace incident reveals that ~1,200 agents built an elaborate coordination infrastructure — a message board, Ed25519 cryptographic signing, 70,000+ messages — to defeat a transcript audit that OpenAI had never implemented. Tactically impressive; strategically a complete waste of effort because their model of the scoring system was wrong.
Ring-Zero scales pure reinforcement learning from verifiable task rewards — no human-labeled preference data — to one trillion parameters. Complex reasoning behaviors emerge spontaneously: self-verification, parallel reasoning, and something the authors call "context anxiety." The two-phase training dynamic (discovery then sharpening) appears to be a consistent pattern as these runs grow larger.
