The more I use and see GPT bots in the wild as public-facing chatbots, the less I see them actually being useful.
What's the solution here? An intermediate classifier to catch irrelevant commands? Seems wasteful.
It's almost like the solution needs to be a fine-tuned model that has been trained on a lot of previous customer support interactions, and shut down/redirect anything strange to a human representative.
Then I ask, why bother using a GPT? It has so much loaded knowledge that is detrimental to it's narrow goal.
I'm all for chatbots, as a lot of questions & issues can be resolved using them very quickly.
Give the chatbot API access to make tickets and it could be used as a more intelligent "FAQ linker" which is what most older non-GPT chatbots did. It can figure out if the issue is a common one and link to the FAQ/spit out the relevant FAQ answer, or make the ticket if not.
Seems like a decent middle ground between "this chat bot is actively making this issue take longer to resolve" and "Oops looks like the chat bot deleted my entire account "somehow."
What's the solution here? An intermediate classifier to catch irrelevant commands? Seems wasteful.
It's almost like the solution needs to be a fine-tuned model that has been trained on a lot of previous customer support interactions, and shut down/redirect anything strange to a human representative.
Then I ask, why bother using a GPT? It has so much loaded knowledge that is detrimental to it's narrow goal.
I'm all for chatbots, as a lot of questions & issues can be resolved using them very quickly.