This is brilliant i can see a use can where the user continually inputs incorrect data or continues to get steps/Processes wrong and on-device training ai will step in an correct user input
Note sentiment analysis, summarization all can get away with incorrectness as well.. we still cannot reliably deploy in a place where it has to be absolutely correct
Hi! Thank you for this!I have a specific use cas I'd like you to go over if you can. A whatsapp chatbot. I think this will be a very common usecase for AI.
Check out all the web sessions at Google I/O → goo.gle/io24-web-yt
Great use case, very representative !
5 stars great talk
This is brilliant i can see a use can where the user continually inputs incorrect data or continues to get steps/Processes wrong and on-device training ai will step in an correct user input
no not autocorrect, but more like a how-to widget, a Microsoft Clipy that only pops up when you unable to complete a Process
OMG!!!
Note sentiment analysis, summarization all can get away with incorrectness as well.. we still cannot reliably deploy in a place where it has to be absolutely correct
Hi! Thank you for this!I have a specific use cas I'd like you to go over if you can. A whatsapp chatbot. I think this will be a very common usecase for AI.
Very informative talk!