LLMs can still be prohibitively expensive for some, and as with all ML models, LLMs are not always accurate. There will always be use cases where leveraging an ML implementation is not the right path forward.  The key considerations for AI project managers to evaluate customers’ needs for AI implementation include: The inputs and outputs required to fulfill your customer’s needs: An input is provided by the customer to your product and the output is provided by your product. So, for a Spotify ML-generated playlist (an output), inputs could include customer preferences, and ‘liked’ songs, artists and music genre. Combinations of inputs and outputs: Customer needs can vary based on whether they want the same or different output for the same or different input. The more permutations and combinations we need to replicate for inputs and outputs, at scale, the more we need to turn to ML versus rule-based systems. Patterns in inputs and outputs: Patterns in the required combinations of inputs or outputs help you decide what type of ML model you need to use for implementation. If there are patterns to the combinations of inputs and outputs (like reviewing customer anecdotes to derive a sentiment score), consider supervised or semi-supervised ML models over LLMs because they might be more cost-effective. Cost and Precision: LLM calls are not always cheap at scale and the outputs are not always precise/exact, despite fine-tuning and prompt engineering. Sometimes, you are better off with supervised models for neural networks that can classify an input using a fixed set of labels, or even rules-based systems, instead of using an LLM.

Read Article