I think this is a moderately strong point of evidence in favor of @1a3orn's hypothesis that chains of thought will become denser forms of existing language rather than new, unintelligible languages.
I think that to be more precise, in this example, a reasoning DSL is used where the rule discovery of syntax rules is obvious, and facilitated by existing meanings of words/symbols/emoji. Human-oriented natural language-based exposition of a development of a representation/theory/solution for a task is similar, but we have more redundancy in our DSL in text repr... (read more)
I think that to be more precise, in this example, a reasoning DSL is used where the rule discovery of syntax rules is obvious, and facilitated by existing meanings of words/symbols/emoji. Human-oriented natural language-based exposition of a development of a representation/theory/solution for a task is similar, but we have more redundancy in our DSL in text repr... (read more)