20B-parameter Alexa model sets new marks in few-shot learning

Re:20B-parameter Alexa model sets new marks in few-shot lear... by visarga on Tuesday August 02, 2022 @05:12PM (#32324357)

Language models can generate code from text instructions. It just needs a training set to learn the target APIs. I expect in the next couple of years to see automated desktop operation (RPA) from text commands, generalising access over human interfaces.

It's really a shame the good language models are not deployed as voice assistants. It would probably be expensive to offer and they don't have the scale necessary. Just to load one of these models you need a $100K computer.

[ Parent | on HN ]

Re:20B-parameter Alexa model sets new marks in few-shot lear... by Closi on Tuesday August 02, 2022 @05:39PM (#32324598)

It also depends what's the biggest priority - I would assume there is a bigger 'quick win' from becoming more reliable at single-intent actions from a market/customer experience perspective rather than pursuing highly complex multi-intent statements.

>99% of commands will be single intent, and they probably work 80% of the time at the moment, so getting those to 99% will have a much bigger short-term impact than focussing on solving the 1% (with the added benfit that once you have solved the first case of getting single-intent right all the time, solving the second more complex queries will be easier as you will have built a more robust base).

[ Parent | on HN ]

Re:20B-parameter Alexa model sets new marks in few-shot lear... by petra on Tuesday August 02, 2022 @07:39PM (#32325725)

I'm curious: what's the leading edge in commercial chatbots?

[ Parent | on HN ]

Re:20B-parameter Alexa model sets new marks in few-shot lear... by speed_spread on Tuesday August 02, 2022 @10:28PM (#32326943)

Hello, I'm Gretta! I'm here to help. It seems you're looking for information on enterprise chatbots geometry. Answer "yes" to access your account's balance or press # for more options.

[ Parent | on HN ]