zlacker

>>isp+(OP)
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.

>>MattDa+Tj
> I'm all for chatbots, as a lot of questions & issues can be resolved using them very quickly.

Can they though? Generally when I chat with customer service it’s because I need a change which cannot (or cannot easily) be done myself.

Giving chatbots the power to make drastic alterations to accounts could potentially cause a lot of problems.

>>infota+Ao
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."