George McGowan, a London software engineer, logged onto Eve Sleep looking to buy a mattress. He was boggled to find that “this website is offering to let me negotiate with an AI to buy a mattress.”…
They use rule-based subsystems, but they also use deep neural approaches. The system diagram on their website (in the “How Nibble uses generative AI” video towards the bottom) shows the following:
The “fact gatherer” and “GPT generative atom” components explicitly use GPT. The “NLU Intent and Entity Models” are classifier components that probably use deep neural approaches, but they don’t say. It’s a good system architecture, it combines the strengths of neural approaches with the strengths of rule-based approaches to address their particular domain, instead just using some massive LLM that tries to do everything.
Of course whether a website actually NEEDS a negotiation chat bot is another question…
It’s a glorified if-else chain, not even close to an AI.
They use rule-based subsystems, but they also use deep neural approaches. The system diagram on their website (in the “How Nibble uses generative AI” video towards the bottom) shows the following:
The “fact gatherer” and “GPT generative atom” components explicitly use GPT. The “NLU Intent and Entity Models” are classifier components that probably use deep neural approaches, but they don’t say. It’s a good system architecture, it combines the strengths of neural approaches with the strengths of rule-based approaches to address their particular domain, instead just using some massive LLM that tries to do everything.
Of course whether a website actually NEEDS a negotiation chat bot is another question…
That does look like an interesting architecture, if implemented correctly. Based on this observation:
The NLU component could be a NER model. However, if the following is true:
It kinda makes the whole system moot in my opinion.
if
almost relieving, really