If you use LLMs, you should use it primarily in ways where it’s easier to confirm the output is valid than it is to create the output yourself. For instance, “what API call in this poorly-documented system performs <some task>?”
There is no consistent definition of AI so you might as well drop the quotation marks, lest you be prescriptivist.
If you use LLMs, you should use it primarily in ways where it’s easier to confirm the output is valid than it is to create the output yourself. For instance, “what API call in this poorly-documented system performs <some task>?”
There is no consistent definition of AI so you might as well drop the quotation marks, lest you be prescriptivist.