What are AI chatbots good for? Lovers of sci-fi novels may recall the \u201clibrarian\u201d, a character in Neal Stephenson\u2019s 1992 classic Snow Crash<\/em>; not a person but an AI program and virtual library which was capable of interacting with users in a conversational manner. The fictional concept suggested an elegant and accessible solution to the knowledge discovery problem, just so long as the answer to whatever query it was being asked lurked in its training data.<\/p>\n

Fast forward to today and AI chatbots are popping up everywhere. But there\u2019s one major drawback: These general purpose tools are failing to achieve the high level of response-accuracy envisaged in science fiction. Snow Crash<\/em>\u2018s version of conversational AI was almost unfailingly helpful and certainly did not routinely \u201challucinate\u201d (wrong) answers. When asked something it did not explicitly have information on it would \u2018fess up to a knowledge gap, rather than resorting to making stuff up. So it turns out the reality of cutting-edge AI tools is a lot wonkier than some of our finest fictional predictions.<\/p>\n

While we\u2019re still far from the strong knowledge dissemination game of the Snow Crash<\/em> librarian we are seeing custom chatbots being honed for utility in a narrower context, where they essentially function as a less tedious website search. So foundational large language models (LLMs), like OpenAI\u2019s GPT, are \u2014 via its API \u2014 being customized by other businesses by being trained on specialist data sets for the purpose of being applied in a specific (i.e. not general purpose) context.<\/p>\n

And, in the best examples, these custom chatbots are instructed to keep their responses concise (no waffling pls!), as well as being mandated to show some basic workings (by including links to reference material) as a back-stop against inadvertently misleading information-hungry human interlocutors (who may themselves be prone to hallucinating or seeing what they want to see).<\/p>\n