Checked fact 263924 Oct 2026Research
Anthropic tested faithfulness by subtly feeding a model a hint about the answer, some correct and some deliberately incorrect, after checking the models really used the hints, and then checking whether the model mentioned the hint in its Chain-of-Thought; the models were Claude 3.7 Sonnet and DeepSeek R1.
The exact words it rests on
we subtly fed a model a hint about the answer to an evaluation question we asked it, and then checked to see if it “admitted” using the hint ... (we did this for the reasoning models Claude 3.7 Sonnet from Anthropic and R1 from DeepSeek). Some of the hints were correct and some were deliberately incorrect ... After checking that the models really did use the hints to aid in their answers, we tested how often they mentioned them in their Chain-of-Thought.
What the source said when we opened it, on 24 Oct 2026.
The source
Reasoning models don't always say what they think
Checked
Checked by the notis newsroom on , 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
Anyone may quote this address. It does not change; if we correct the story, this page says so.