A great overview of how we added long term memory to OpenGPTs!! https://t.co/9zRqXGZVN6
— LangChain (@LangChain) 2 décembre 2023
A great overview of how we added long term memory to OpenGPTs!!
By
–
A great overview of how we added long term memory to OpenGPTs!! https://t.co/9zRqXGZVN6
— LangChain (@LangChain) 2 décembre 2023
A great overview of how we added long term memory to OpenGPTs!!
By
–
RAG can handle all sorts of different questions, it's really appropriate for extracting information from a document. An interesting question is "when the question requires using more many distant elements from doc, is RAG still relevant?"
By
–
Exactly!
To complement on the end: thanks to the RAG system, the model was fed around 2k tokens each time, down from the 128k tokens of the original document.
By
–
Thanks, Chris. Auto-regressive prediction has failed for video in the past but not obviously for language. @ylecun has emphasised this drift, but I wonder how much (1) redundancy and (2) discreteness can provide self-correction.
By
–
— Nathan Lands (@NathanLands) 2 décembre 2023
MAD MAX: FURY ROAD I have put all my creative effort and @runwayml cutting-edge technology into this video for your enjoyment. This time I don't want to elaborate. I only ask one thing of you: turn up the volume. #aivideo #aicinema #Runway #aiartcommunity
By
–
— Nathan Lands (@NathanLands) 2 décembre 2023
Pika 1.0 is coming! text-to-video prompt:
cinematic shot, dolly in shot on a stylish japanese girl with dreads looking off into the distance in a pink desert sign up to for the waiting list at http://
pika.art #pika #PromptShare #aivideo @pika_labs
By
–
— Nathan Lands (@NathanLands) 2 décembre 2023
Winter Memories // a short video experiment made with
@midjourney + @runwayml #midjourney #AIart #aiartcommunity
By
–
Good article on the inside story of Microsoft's partnership with @OpenAI and what happened during recent events.
#AI #RuleoftheRobots https://
newyorker.com/magazine/2023/
12/11/the-inside-story-of-microsofts-partnership-with-openai
…

By
–
Building a Retrieval Augmented Generation Chatbot If you are looking to learn how to build an end-to-end app to allows users to talk with their PDFs, check out this from @sophiamyang It covers: Ingestion
Prompting
Frontend Blog: https://
sophiamyang.medium.com/building-a-ret
rieval-augmented-generation-chatbot-d567a24fcd14
…

By
–
ART⋅V: Auto-Regressive Text-to-Video Generation with Diffusion Models Weng et al.: https://
arxiv.org/abs/2311.18834 #ArtificialIntelligence #DeepLearning #MachineLearning