Code as a Tool for Thought

LLMs are probabilistic and approximate, while mathematics and logic require deterministic precision. Division of labor: LLMs are responsible for understanding the task and writing the code, the interpreter – for accurate calculations. Example: a problem about the percentage of students is easily solved incorrectly “in the head”, but the code gives an accurate, verifiable result. Wolfram scheme: LLM understands natural language and formalizes the problem, a symbolic engine (SymPy, Mathematica) solves it accurately. There is a reciprocal relationship between the model and the harness: the weaker the model, the more logic needs to be moved into the code and constraint solvers.

Related: [Code as a meta-ability], [Seven basic tools]