It is wild that we still ask LLMs to think in plain text — the next 10x is in the latent stream.

Karpathy argues the next 10x in reasoning quality will come from latent-space CoT, not better text-based chains.

Key Points

• Plain-text CoT is an extraordinary information-loss interface.
• Latent reasoning bypasses tokenisation overhead.
• Likely path to the next major capability jump.