Chain-of-Thought

Audit logs are comforting because they look administrative. A system acts, a trace appears, a reviewer nods, and everyone pretends the record explains the decision. That habit becomes more fragile when the system is an AI model. In many current AI workflows, especially those involving reasoning models or autonomous agents, the chain-of-thought is treated as the closest available thing to an internal audit trail. The model writes down intermediate reasoning, a monitor reads that reasoning, and the organization hopes the dangerous part—deception, hidden goals, sandbagging, sabotage, or simply the decisive cue behind an answer—will be visible before the final action causes trouble. ...

Wait. That tiny word has become one of the more over-interpreted stage props in modern AI. A model writes a few lines of algebra, pauses with “Wait, is that correct?”, then revises itself. The demo looks satisfying. It gives the impression of a machine catching itself in the act of thinking. A new paper by Jeonghye Kim and co-authors argues that this interpretation is a little too theatrical.1 The useful question is not whether “Wait” is a magic reasoning token. It is not. The useful question is why some models can interrupt a locally plausible but globally wrong reasoning path before the error becomes unrecoverable. ...

Audit trails are boring until something goes wrong. In ordinary business operations, this is not controversial. If a payment approval, legal review, procurement decision, or trading order leaves intermediate records, people can reconstruct what happened. If the whole decision is buried inside a black-box system that simply outputs “approved,” “rejected,” or “buy now,” the audit team has a less glamorous job: guessing which invisible machinery produced the visible answer. Charming, in the way dental surgery is charming. ...

A chatbot answers. An agent checks. That distinction sounds small until a workflow fails at 2:17 p.m. because the model confidently invented a policy clause, skipped the database lookup, and then explained itself with the serene authority of a consultant who has already left the building. The 2022 paper ReAct: Synergizing Reasoning and Acting in Language Models matters because it made that failure mode harder to ignore.1 It did not simply ask language models to “think step by step.” Chain-of-thought prompting already did that. It did not simply attach a search box to a model. Retrieval-augmented systems were already moving in that direction. The paper’s real contribution was more architectural: it showed that a language model could alternate between reasoning, acting, observing, and revising its next move. ...

A fire alarm can cause people to evacuate. It can cause a building to enter alert mode. It can trigger emergency procedures, bring firefighters, and make everyone suddenly remember where the stairs are. But does a fire alarm cause a fire? Obviously not. At least, obviously not to a human who understands the causal structure. The alarm is usually an effect or signal of fire risk, not the origin of the fire itself. A model trained on enough sentences of the form “fire alarm causes…” may not be so careful. It may see the familiar phrase pattern, complete the familiar answer, and walk directly into the wrong conclusion with excellent grammar. ...

The familiar ritual: ask it to think longer When an LLM gives a weak answer, the standard reflex is now almost ceremonial: ask it to think step by step. The model writes more. The answer often improves. The benchmark number rises. Everyone feels temporarily reassured. This habit has become so normal that many teams treat chain-of-thought as if it were a small reasoning engine bolted onto the model: more intermediate steps, more deliberate thought, more correctness. A comforting story. Also, like many comforting stories in AI, not quite what the evidence says. ...

Reasoning budgets look harmless until they become a line item. A user asks an AI system to reconcile a long contract, inspect a transaction trail, trace dependencies in a knowledge graph, or verify whether one operational event can lead to another. The model “thinks.” The answer improves. The invoice also improves, in the less charming direction. The usual response is to ask for shorter reasoning: compress the chain of thought, use fewer tokens, impose a budget, maybe add a prompt that says “be concise,” because apparently invoices can be negotiated with adjectives. ...

Paper is a good trap for artificial intelligence. Fold it, punch it, unfold it, and ask where the holes are. A person may not solve the problem instantly, but the mind knows what to do: imagine the folded sheet opening step by step. The reasoning is not mainly verbal. We do not narrate every cell of the paper grid like a bored accountant reading inventory codes. We see the transformation. ...

Audit is a less glamorous word than intelligence. That is unfortunate, because most business problems with AI agents do not begin with stupidity. They begin with confidence. The agent gives an answer. The answer sounds reasonable. The explanation sounds even better. A manager, analyst, compliance reviewer, or product owner reads the chain of thought and feels the mild comfort of seeing steps. There is a premise, then a bridge, then a conclusion. Very civilized. Very inspectable. Very possibly fake. ...

A bad answer is easy to audit. It sits there, smug and wrong. A bad reasoning process is worse. It looks useful while it is drifting. It explains itself. It produces intermediate steps that sound locally plausible. It may even correct one mistake while preserving another, like a spreadsheet with a broken formula hiding behind tasteful formatting. ...