Feels to me like a bit of a reputation risk to @lmsysorg though if this is indeed a stealth model launch They're supposed to be a neutral benchmarking tool, it's not a great look if they're working behind-the-scenes with model vendors in an opaque manner like this
GENERATIVE AI
-
New GPT2 Chatbot Impresses with Better Search Results
By
–
You can try out the mysterious gpt2-chatbot at https://
chat.lmsys.org (select "Direct Chat" and pick it from the menu) Initial impressions: I'm very impressed. It gave me a better answer for an ego search ("Who is Simon Willison?") than any other model I've tried -
Record Manager: Keeping RAG Indexes Updated and Optimized
By
–
Keeping your indexes up to date with latest changes in your documents is crucial in building a RAG.
— FlowiseAI (@FlowiseAI) 29 avril 2024
And Record Manager is here to help with:
🗄️Prevent duplicated contents
💰Save cost on embeddings
🧹Cleanup outdated content@leonvz did a great job of explaining it, watch it👇 https://t.co/2gsSFJHTvk pic.twitter.com/zUynk70O6vKeeping your indexes up to date with latest changes in your documents is crucial in building a RAG. And Record Manager is here to help with:
Prevent duplicated contents
Save cost on embeddings
Cleanup outdated content @leonvz did a great job of explaining it, watch it -
ChatGPT Memory Feature Now Available for Plus Users
By
–
Memory is now available to all ChatGPT Plus users. Using Memory is easy: just start a new chat and tell ChatGPT anything you’d like it to remember.
— OpenAI (@OpenAI) 29 avril 2024
Memory can be turned on or off in settings and is not currently available in Europe or Korea. Team, Enterprise, and GPTs to come. pic.twitter.com/mlt9vyYeMKMemory is now available to all ChatGPT Plus users. Using Memory is easy: just start a new chat and tell ChatGPT anything you’d like it to remember. Memory can be turned on or off in settings and is not currently available in Europe or Korea. Team, Enterprise, and GPTs to come.
-
Constrained Sampling Forces Model Function Calls
By
–
Constrained sampling to ensure that a model calls a function:
-
Analytics-Driven Content Creation Fails to Capture Authentic Taste
By
–
I feel like this applies to…everything these days. Taste is so important and people will pay for it. There's so much garbage and sameness and my theory is people are tired of getting 'what they want,' which really means, what a bunch of soulless analytics *say* people want. But
-
Prompt Engineering for Vision Models: Generation, Editing, Detection
By
–
In Prompt Engineering for Vision Models, taught by @anmorgan2414 @JacquesVerre and @KaiserFrose of @Cometml , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for… pic.twitter.com/sXis2waFDH
— Andrew Ng (@AndrewYNg) 29 avril 2024In Prompt Engineering for Vision Models, taught by @anmorgan2414 @JacquesVerre and @KaiserFrose of @Cometml , you’ll learn how to prompt and fine-tune vision models for personalized image generation, image editing, object detection and segmentation. The prompts you'll use for
-
Llama 3 Models Now Available on Poe Across All Platforms
By
–
Both https://
poe.com/Llama-3-70b-Gr
oq
… and https://
poe.com/Llama-3-8b-Groq are available across the Poe iOS, Android, Mac, and Windows apps. (2/2) -
Llama 3 70B Groq inference now available on Poe
By
–
Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2) pic.twitter.com/F6bXca7LoH
— Poe (@poe_platform) 29 avril 2024Groq-powered inference for Llama 3 is now available on Poe! You can use Llama-3-70b-Groq and experience the state-of-the-art open source model with near-instant streaming. (1/2)
-
ChatGPT Enhances News Content Through Financial Times Partnership
By
–
We’ve partnered with @FT to enhance news content in ChatGPT and collaborate on new AI experiences for FT readers.