Build a RAG app with Llama-3 running locally on your computer
(100% free and without internet):
GENERATIVE AI
-
Build Local RAG App with Llama-3 Offline
By
–
-
New Assistants API Sample App with Next.js Released
By
–
Introducing a new sample app to help you get started with the Assistants API and @nextjs
! Great work by @ilanbigio and @karoliskosas
. Let us know what you need next—we can’t wait to see what you build! https://
github.com/openai/openai-
assistants-quickstart
… -

Vibe-Eval Wins Best Evaluation Benchmark Name Prize
By
–
Vibe-Eval wins the prize for the best name for an eval benchmark, surprised no-one had taken that name already
-

AI Safety and Cybersecurity Future Panel at RSAC
By
–
Attending #RSAC? Don't miss this keynote panel including Daniel Rohrer, VP of Product Security, NVIDIA discussing the rise of #AI safety and what it means for the future of AI and cybersecurity. https://
nvda.ws/3xYEl59 -
1 Trillion Edges: Breakthrough in AI Model Architecture
By
–
An edgy post… 1 trillion edges, in fact! https://t.co/ymbl16TL2X
— Jeff Dean (@JeffDean) 1 mai 2024An edgy post… 1 trillion edges, in fact!
-
Beyond ChatGPT: 5 AI Game-Changers
By
–
Beyond ChatGPT: 5 AI Game-Changers AI tools revolutionize marketing. • Embrace emotional analytics
• Leverage generative AI
• Implement AR tactics Read more: https://
godofprompt.ai/blog/ai-your-m
arketing-team-should-use-now
… -
ComfyUI Camp Setup at Mars College Next Year
By
–
not LA but we’d love to set something up at @Mars_College next year, couple hours away. we basically have a ComfyUI camp there, a lot of space, and like 20 projectors …
-

Dedicated translation button in Copilot Android app
By
–

Copilot app on Android got a dedicated translation button. In case you are too shy to ask the chat itself
-
Why Open Source AI Models Lag Behind Commercial Solutions
By
–
Several people told me to add "open source performance is still lagging compared to commercial models". Is there any fundamental reason that stops open source models from catching up? The biggest reason I can think of is what @soumithchintala told me: open source models don't
