Data storytelling is indeed a crucial thing!!
INNOVATION
-
Postal Robot Revolutionizes Mail Delivery in Germany
By
–
There are some who believe that artificial intelligence and robotics won't all together replace humans, but fill a task. This postal robot – revolutionizing mail delivery in Germany – is an example of that. #CES2023 #CES23 #AI #IoT #futureofwork #Robotics #SaturdayMorning #ML #EU pic.twitter.com/COf9pJ9vbZ
— Sean Gardner (@2morrowknight) 7 janvier 2023There are some who believe that artificial intelligence and robotics won't all together replace humans, but fill a task. This postal robot – revolutionizing mail delivery in Germany – is an example of that. #CES2023 #CES23 #AI #IoT #futureofwork #Robotics #SaturdayMorning #ML #EU
-
ChatGPT Impresses with Code Understanding but Makes Logic Error
By
–
That thread is what made me go attempt to do some of my work today with ChatGPT — optimizing a chunk of logic was on my todo list, so I asked ChatGPT. I was really impressed by how it understood the code, but then it made the logic error.
-

The Jetsons Predicted Telemedicine 60 Years Ago
By
–
Telemedicine forecast by “The Jetsons” (in 1962). #CES2023 #CES23 #telemedicine #DYK #AI #iot (via @BeschlossDC
) #healthcare -
Robot Helper to Automate Snow Shoveling This Winter
By
–
Tired of shoveling snow this winter? This robot will help you out and clean the way. #CES23 #CES2023 #ces #ArtificialIntelligence #AI #tech pic.twitter.com/USnav6jgi8
— Sean Gardner (@2morrowknight) 7 janvier 2023Tired of shoveling snow this winter? This robot will help you out and clean the way. #CES23 #CES2023 #ces #ArtificialIntelligence #AI #tech
-
Denoising Errors Transformed Into Image Generation via Diffusion
By
–
When denoising goes haywire and makes stuff up, call it diffusion and use it for image generation.
-
AUTOMATIC1111 High Resolution Fix Implementation Guide
By
–
Yes! AUTOMATIC1111 has "High res fix", need to figure out how to do this myself
-
Beyond Text: Multimodal AI’s Stunning Potential Beyond GPT
By
–
Wrong lesson from GPT paradigm — text is all you need. Other modalities will be incredibly stunning. Can feel it already from DALL-E, which can do something quite useful despite its nascent language ability.
-
Training Costs Stable Diffusion 512 768 4K Models Data
By
–
SD 512 cost $600k to train, SD 768 probably $1.3M and 4K would cost $10M I think to train also where do you source billions of images
-
Training costs for stable diffusion models scale exponentially
By
–
SD 512 cost $600k to train, SD 768 probably $1.3M and 4K would cost $10M I think to train also where do you source billions of images