satorii
Re:Evolution of Fast and Efficient Transformer
on Monday September 13, 2021 @12:02PM (#28513147)
Transformer optimization and acceleration
Re:On the Opportunities and Risks of Foundation Models
on Monday August 23, 2021 @06:20PM (#28282742)
Interesting findings! Not sure about whether it is within certain research communities or a broader trend.
But Clip cloud be a good plug-in for nowadays writings/design then, something like Clip empowered unsplash.
Transformer, the model architecture of the year comes to Computer Vision
Re:Low-code, no-model recommendation system with GPT3
on Wednesday September 09, 2020 @05:46PM (#24426320)
Cool! I will drop you a message or catch up with you on openai-api slack.
There are a couple of features we see GPT3 stands out and potentially benefits the product features.
Currently we are evaluating the end to end quality and cost versus our traditional ML based recommendation and semantic search pipeline.
Re:Low-code, no-model recommendation system with GPT3
on Wednesday September 09, 2020 @01:59PM (#24423820)
assume each prediction use 1000 tokens (including both input prompt and output text), then 100k tokens -> 100 predictions
Re:Low-code, no-model recommendation system with GPT3
on Wednesday September 09, 2020 @11:25AM (#24422048)
Thanks for pointing out the errors. I got them fixed in the blog.
This is also a good use case of GPT3, checking grammar and spelling. I might build an application for this.
Low-code, no-model recommendation system with GPT3
Re:Building Jarvis
on Monday December 19, 2016 @09:57PM (#13217061)
Amazed by how much work he has done in 100 hours while running one of the world's largest internet company. If anyone interested in trying out some of the "Jarvis" without hacking, checking out https://saymosaic.com. We have put together a tool to enable you interact with your smart devices/services with either voice on Echo or text on FB messenger. Currently, it is in beta with more integrations and aggregated services to come.