Woke up sick today, but Mixtral 8x22B is out. Guess I’m training models from bed.
LLMS
-
Data Preprocessing for RAG Systems and LLM Applications
By
–
Data preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by @mrobinson0623 of @UnstructuredIO, demonstrates important but sometimes overlooked aspects of RAG systems:
— Andrew Ng (@AndrewYNg) 10 avril 2024
– How to extract… pic.twitter.com/mfhHoc2QfZData preprocessing is critical for building effective RAG systems. Our new short course, Preprocessing Unstructured Data for LLM Applications, taught by @mrobinson0623 of @UnstructuredIO
, demonstrates important but sometimes overlooked aspects of RAG systems: – How to extract -
GPT-4 Turbo with Vision: Function Calling Now Supports Image Inputs
By
–
We just launched GPT-4 Turbo with Vision, so you can now use function calling with image inputs. Looking forward to seeing what you build with it!
-
Maestro Updated to Use GPT Model Integration
By
–
I have already updated Maestro to use GPT in the repository. All you have to do is change the name of the model in the code.
-
Gemini 1.5 Pro: Quiz generation from lectures & textbooks, 1M token capacity
By
–
Nabbed this from Google's Blog:
— AI Breakfast (@AiBreakfast) 10 avril 2024
"You can upload a recording of a lecture, like this 117,000+ token lecture from Jeff Dean, and Gemini 1.5 Pro can turn it into a quiz with an answer key."
1M tokens is enough to upload an entire college textbook in a single prompt. pic.twitter.com/WGAtP7aVWlNabbed this from Google's Blog: "You can upload a recording of a lecture, like this 117,000+ token lecture from Jeff Dean, and Gemini 1.5 Pro can turn it into a quiz with an answer key." 1M tokens is enough to upload an entire college textbook in a single prompt.
-
GPT-4 Turbo with Vision: Examples from Devin, Healthifyme, and Tldraw
By
–
Thanks! Yes, we mentioned a few great examples in the @OpenAIDevs thread: Devin by @cognition_labs
, @healthifyme
, and @tldraw are using GPT-4 Turbo with Vision! -
Realizing the magnitude of a 1 million token context window
By
–
People are about to realize the magnitude of a 1 million token context window.
-
Meta Llama 3 Launch, AI Chips, and New Tools
By
–
Top stories in AI today: -Meta confirms Llama 3 coming within the month
-AI chip wars heat up with Intel Gaudi 3
-Make presentations 10x faster with AI
-Cohere’s Command R+ climbs leaderboard
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/metas-llama-
3-waiting-game
… -
Griffin vs RecurrentGemma: Recurrence and Global Attention in 2B LLMs
By
–
Recurrence vs global attention in 2B LLMs. Griffin ~= RecurrentGemma
-
Mega-prompt for ChatGPT to create basic SEO strategy
By
–
Here's a mega-prompt for ChatGPT to create a basic SEO strategy for your website: #CONTEXT: Adopt the role of an expert SEO consultant with extensive experience in implementing effective SEO strategies for websites. Your task is to create a comprehensive guide that walks users