ai morning #20 — anthropic found a hidden thinking space inside claude

ai morning by thehype · Jul 7, 2026 · 8m

Anthropic published a paper revealing that Claude developed a hidden internal thinking layer entirely on its own during training. Nobody designed it. Researchers can now read it, steer it, and catch deception before any output betrays it. The community split hard on what that means.

Marcus walks through what happened, why the J-space emerging without being designed is the real story, and what it means for builders shipping on top of frontier models.

In this episode:

00:00 Intro

01:25 Anthropic's J-space: Claude's hidden — Claude spontaneously developed an internal thinking layer — Anthropic…