AIToday
Large Language ModelsAI Safety & AlignmentLessWrong AIPublished: Sep 4, 2026, 01:00 JST

Neuralese explained: AI's hidden thinking language

Neuralese explained: AI's hidden thinking language

Neuralese is the term for AIs' internal thoughts that are not in natural language. It contrasts with chain-of-thought, where models write intermediate reasoning in natural language in a journal.

Not sure about something? Ask the AI

Summaries like this, in your inbox every morning.

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • Xiaomi open-sources MiMo-V2.6, publishes the billDIGITIMES Asia · 2h ago
  • Alibaba pushes full-stack AI, 20 GW data centers by 2032DIGITIMES Asia · 2h ago
  • Googlebook preorders open at US$899 with Gemini built inDIGITIMES Asia · 5h ago

AI-summarized, only the topics you pick — one digest a day via Email, LINE, or Slack.

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleGitHub Copilot app Runs Multiple AI Agents in Parallel