Checked fact 264524 Oct 2026Research

The abstract says in settings like theirs, where Chain-of-Thought reasoning is not necessary, test-time monitoring of Chain-of-Thoughts is unlikely to reliably catch rare and catastrophic unexpected behaviours.

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

They also suggest that in settings like ours where CoT reasoning is not necessary, test-time monitoring of CoTs is unlikely to reliably catch rare and catastrophic unexpected behaviors.

What the source said when we opened it, on 24 Oct 2026.

The source

Reasoning Models Don't Always Say What They Think
arXiv (Anthropic Alignment Science) · 2025-05-08

Open the source archived copy

Checked

Checked by the notis newsroom on 24 Oct 2026, against the source above.

In the story

Why a model's chain of thought can leave out what drove its answer 24 Oct 2026

Cite this fact

Short permanent address

In a sentence

“The abstract says in settings like theirs, where Chain-of-Thought reasoning is not necessary, test-time monitoring of Chain-of-Thoughts is unlikely to reliably catch rare and catastrophic unexpected behaviours.” ai notis, checked 24 Oct 2026. Source: Reasoning Models Don't Always Say What They Think (arXiv (Anthropic Alignment Science)). https://ainotis.com/c/2645

As a reference (APA style)

ai notis. (2026, October 24). The abstract says in settings like theirs, where Chain-of-Thought reasoning is not necessary, test-time monitoring of Chain-of-Thoughts is unlikely to reliably catch rare and catastrophic unexpected behaviours [Checked claim 2645]. ai notis. https://ainotis.com/c/2645

Anyone may quote this address. It does not change; if we correct the story, this page says so.