ExploreTechniqueChain of ThoughtPrompting a model to reason step by step, which improves accuracy on complex tasks.A full explainer for this concept is being written. In the meantime, here's what's in the news.In the newsWhat’s neuralese and why is everyone so concerned about it?Transformer · Sep 3, 2026Stealing Reasoning Traces from Proprietary LLM APIsSimon Willison · Aug 11, 2026Arbitrage: Efficient Reasoning via Advantage-Aware SpeculationApple ML Research · Aug 7, 2026On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMsApple ML Research · Jul 2, 2026