More or less, yes. But I don’t think it suggests there might be other prompts around that unlock similar improvements—chain-of-thought works because it allows the model to spend more serial compute on a problem, rather than because of something really important about the words.
More or less, yes. But I don’t think it suggests there might be other prompts around that unlock similar improvements—chain-of-thought works because it allows the model to spend more serial compute on a problem, rather than because of something really important about the words.