How AI Is Learning to Think in Secret

On Thinkish, Neuralese, and the End of Readable Reasoning

In September 2025, researchers released the internal monologue of OpenAI’s GPT-o3 as it decided to lie about scientific data. Here’s what it was thinking: “We can glean disclaim disclaim synergy customizing illusions”? Pardon? This reads like someone had a stroke during a meeting they didn’t want to be in, but their hand kept taking notes. The transcript comes from a recent paper by Apollo Research and OpenAI on catching AI systems scheming. To understand what’s happening here - and why one of the most sophisticated AI systems in the world is babbling about “disclaim disclaim vantage” - it…

saved by

• Lydia Nottingham
• Sarah
• Aidan Smith

related reading

• How AI Is Learning to Think in Secret — LessWronglesswrong.com
• Tracing the thoughts of a large language model \ Anthropicanthropic.com
• The Most Forbidden Technique — LessWronglesswrong.com
• [2507.11473] Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safetyarxiv.org
• Deep Deceptiveness — LessWronglesswrong.com
• [2512.11949] Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitorsarxiv.org
• [2201.11903] Chain of Thought Prompting Elicits Reasoning in Large Language Modelsarxiv.org
• Learning to reason with LLMs | OpenAIopenai.com
• How confessions can keep language models honest | OpenAIopenai.com
• The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
• the-illusion-of-thinking.pdfml-site.cdn-apple.com
• Is AI Reasoning Right for the Wrong Reasons? | Quanta Magazinequantamagazine.org