Se buscan llaves de coche perdidas en El Cañaveral.
Zona 📍Parque entre Imperio Argentina y Fco. Grande Covián, Miguel Delibes, José Escobar y Valiente y Victoria Kent.
Un saludo
@LostInCanaveral
@villamorforever Juan Carlos, muchas gracias por los grandes momentos que nos has hecho pasar en la vuelta. Eres un profesional como la copa de un pino. Se va a echar en falta el clásico:
-¡Moto!
-¡Juan Carlos!
Grandes entrevistas, grandes preguntas, siempre aportando lo mejor.
*If* GPT-4 is multimodal, we can predict with reasonable confidence what GPT-4 *might* be capable of, given Microsoft’s prior work Kosmos-1:
- Visual IQ test: yes, the ones that humans take!
- OCR-free reading comprehension: input a screenshot, scanned document, street sign, or any pixels that contain text. Reason about the contents directly without explicit OCR. This is extremely useful to unlock AI-powered apps on multimedia web pages, or “text in the wild” from real world cams.
- Multimodal chat: have a conversation about a picture. You can even provide “follow-up” images in the middle.
- Broad visual understanding abilities, like captioning, visual question answering, object detection, scene layout, common sense reasoning, etc.
- Audio & speech recognition (??): wasn’t mentioned in Kosmos-1 paper, but Whisper is already an OpenAI API and should be fairly easy to integrate.
Note: the predictions are based on what Andreas Braun, Microsoft Germany CTO, allegedly said. They may or may not be accurate (that’s why I call it “prediction”). But Kosmos-1 is very real and rock solid. It offers a glimpse of either GPT-4 or whatever AI service that Microsoft will provide next. I find it difficult to believe Kosmos-1 will stay in the lab and not become a product.
In any case, prepare yourself for multimodal APIs - they’ll happen sooner or later!
My book Analyzing US Census Data is now in print! I’m really happy with how it turned out.
Thanks so much to @lara_crc and the @CRCPress team. You can order your copy today! https://t.co/6F32TSlyT2; https://t.co/zdG0wmqN60
#rstats
Raster Vision is the most interesting open source project I ever had the pleasure of seeing get built up close - as we enter golden age of AI, free and open tools for applying new techniques to satellite imagery are going to be invaluable! https://t.co/hrYIHaLRXL