If I need something that does have answers that can be definitely wrong in important ways, and where I’m not an expert in the subject, or don’t have all the underlying data memorised and would have to repeat all the work myself to check it, then today, I can’t use an LLM for that at all.
Ben Evans shares a rule for deciding when to use an LLM. In his post, he suggests that considering whether a task is probabilistic or deterministic in nature helps with that decision.
Visit the source: ben-evans.com