Some interesting illustrations on embedding. From the book, "Super Study Guide: Transformers & Large Language Models" Has a lot of nice illustrations.

Last month, I managed 5 client projects using Cursor + V0, all while working a full-time job, and I think I’ve finally cracked the formula for efficiency with minimal mistakes. Here’s everything I’ve learned to make AI work for you. THREAD BELOW

Cursor employees came to share their Cursor workflow while building Cursor. When builders == users, product UX is elite. I love ian's config. Super silly to see on the big auditorium screen 💀 trust it works Paste in Settings > Rules for AI👇 `DO NOT GIVE ME HIGH

Goodbye, vanilla RAG. Hello, Agentic RAG! 𝗩𝗮𝗻𝗶𝗹𝗹𝗮 𝗥𝗔𝗚 The common vanilla RAG implementation processed the user query through a retrieval and generation pipeline to generate a response grounded in external knowledge. Advanced vanilla RAG techniques include e.g.,

In 1974, Steve Jobs came to India in search for enlightenment. 7 months later, he returned with a philosophy that would later build Apple into a $1 trillion empire. Here’s the philosophy: 🧵

2023: RAG is all you need 2024: AI agents are all you need Now bringing you the fusion of AI agents and RAG pipelines. In our recent blog post @ecardenas300 and I lift the curtains of agentic RAG. We discuss: • What is agentic RAG • Architectures of agentic RAG • How to

Working on a guide to self-host open LLMs.. 👀 The stack involves: - vLLM or TGI - containerized using Docker - deployed on Kubernetes on Google Cloud Interested to learn more? See cloud.google.com/kubernetes-eng… for a good intro

🚨This week’s top AI/ML research papers: - LLaVA-o1 - Marco-o1 - The Dawn of GUI Agent - Hymba - When Precision Meets Position - Multimodal Autoregressive Pre-training of Large Vision Encoders - Generative World Explorer - That Chip Has Sailed - Is Your LLM Secretly a World

github.com/astriaai/heads…

We’ve had a lot of asks for better table/chart/image extraction capabilities from images for e2e agent pipelines. While in RAG, the LLM context window itself doesn’t necessarily need this finer-grained segmentation, these capabilities help with citations in the source document,

UI Movie Review!! #UiTheMovie #Upendra #Kannada

10 days since launch: 1,250+ builders have created 1,000+ agents on Lyzr AI Agent Studio! 🚀 From Fortune 100 giants (Amazon, HP, Google) to Academicians (MIT, IEEE) & enterprise startups, everyone’s building 🛠️ on Lyzr. Even our competitors! 😉 We’re making your work life more

We haven’t reached full potential yet. DeepScaleR is a 1.5B parameter model fine-tuned with Reinforcement Learning that surpasses OpenAI's O1-preview in math benchmarks, proving RL scaling is effective even for smaller models. Recipe: 0️⃣ Started from

Anthropic has released a full guide to building AI Agents There's both a YT video and a detailed blog post with all the necessary tips. Everything you need to know below (And links to resources)

Reminder: Sindoor is pious to Indians 🙏

ऑपरेशन सिंदूर... जय बजरंगबली 🔥 #OprationSindoor #IndiaPakistanWar

If you're getting into LLMs, PyTorch is essential. And lot of folks asked for beginner-friendly material, so I put this together: PyTorch in One Hour: From Tensors to Multi-GPU Training (sebastianraschka.com/teaching/pytor…) 📖 ~1h to read through 💡 Maybe the perfect weekend project!? I’ve

Neo is the Cursor for ML Engineers. Just like Cursor changed how devs write code- Neo AI is doing the same for ML engineers. No prompts. No notebooks. Just results. Here’s what makes it wild → heyneo.so/waitlist

Cool ChatGPT usecase. With an AR/VR glasses it will be so much more magical. Prompt: “I’m about to go for a walk around [CITY/PLACE]. Can you act as my live tour guide? As I tell you which streets or landmarks I’m passing, give me interesting facts, stories, and historical