Next-generation artificial intelligence models for text generation deliver the technology needed to finally make chat bots work.
It has often been said that chat bots arrived too early - when technology wasn’t there yet. We all know that talking to them feels more like filling out a form than a conversation, they fail as soon as you go slightly off the script. They are also time-consuming to set up, require a specialised library or tool.
Large text generation models like GPT-3 are a true breakthrough but cannot by themselves be served as a product for two main reasons. First of all, having been trained on vast quantities of diverse texts, they can drift away from their assigned topic and provide potentially misleading, incorrect or even dangerous information. Secondly, a truly useful chat bot would not be based purely on general knowledge but rather would make use of a knowledge base specific to the particular task at hand.
That’s why we built our Quickchat bot engine on top of GPT-3. It takes care of:
- making sure the chat bot doesn’t drift away from the topic it was assigned,
- priming the chat bot with knowledge base specific to a particular use case.
How does it work?
Where do I start?
- Please get in touch at firstname.lastname@example.org and provide basic information about your use case (tasks chat bot is expected to accomplish, describe knowledge base to be provided to chat bot, where it will be deployed, expected traffic).
- We will be in touch shortly to discuss further and arrange your Proof of Concept.