• When we prompt a large language model (LLM) to solve a complex polynomial equation, it does not just return an answer but uses its “chain of thought” to work through a solution • In a sense, the LLM behaves like a computer, a machine that computes the solution • But this machine is quite unlike what Alan Turing described as a universal model of computation almost 90 years ago • In what sense can an LLM be thought of as a computer • Can it be universal, that is, able to solve any computable task, as a Turing machine does • If so, how does it learn this ability from finite data

Article Summaries:

  • When we prompt a large language model (LLM) to solve a complex polynomial equation, it does not just return an answer but uses its “chain of thought” to work through a solution. In a sense, the LLM behaves like a computer, a machine that computes the solution. But this machine is quite unlike what Alan Turing described as a universal model of computation almost 90 years ago. In what sense can an LLM be thought of as a computer? Can it be universal, that is, able to solve any computable task, as a Turing machine does? If so, how does it learn this ability from finite data? Current theories of m

Sources: