BusyinPassingtime
@gauravGRV
Data Scientist, Machine learning , python , d3js etc.
คุณอาจชื่นชอบ
Why do RAG systems feel like they hit a ceiling? I've been diving into @helloiamleonie's latest article on agent memory, and it provided so much clarity into the current evolution of RAG systems. The progression from RAG → Agentic RAG → Agent Memory isn't about adding…
🚨 RAG is dead. Long live Agentic RAG. 2025 isn’t about retrieval or generation anymore it’s about decision-making systems that can think, route, reflect, and correct themselves. Every serious AI builder I know is moving from basic RAG pipelines to Agentic RAG architectures…
AI Agent Learning Roadmap. Grab the AI Agent Handbook: codewithdhanian.gumroad.com/l/gfkbh
Your RAG system is failing? It's not your vector database - it's how you're chunking your data. Everyone focuses on picking the perfect vector database or embedding model. But here's what actually makes or breaks your RAG system: how you prepare your data before it ever gets…
I built Multi-Head Attention in Excel because I wanted to understand how it works. It helped me — now it can help you too. 🔽 Download: byhand.ai/mha
Here's a common misconception about RAG! Most people think RAG works like this: index a document → retrieve that same document. But indexing ≠ retrieval. What you index doesn't have to be what you feed the LLM. Once you understand this, you can build RAG systems that…
A simple trick cuts your LLM costs by 50%! Just stop using JSON and use this instead: TOON (Token-Oriented Object Notation) slashes your LLM token usage in half while keeping data perfectly readable. Here's why it works: TOON's sweet spot: uniform arrays with consistent…
5 LLM fine-tuning techniques, explained visually:
🚨 Anthropic just solved the problem every AI agent engineer’s been screaming about for a year. Every agent today burns tokens like fuel every tool call, every definition, every intermediate result jammed into context. Now Anthropic’s introducing the fix: code execution with…
LLM vs RAG vs Agent Workbook ~ Download byhand.ai/p/llm-vs-rag-v… Let me first share my philosophy behind building this new AI by Hand ✍️ workbook. What I want to build is not an art gallery filled with pretty diagrams for you to admire from a distance. What I want to build is…
Integrating 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗥𝗔𝗚 Systems via 𝗠𝗖𝗣 👇 If you are building RAG systems and packing many data sources for retrieval, most likely there is some agency present at least at the data source selection for retrieval stage. This is how MCP enriches the evolution of…
Here's my beginner's lecture series for RAG, Vector Database, Agent, and Multi-Agents: Download slides: 👇 * RAG: byhand.ai/p/beginners-gu… * Agents: byhand.ai/p/beginners-gu… * Vector Database: byhand.ai/p/beginners-gu… * Multi-Agents: byhand.ai/p/beginners-gu… --- 100% original,…
The main 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗗𝗲𝗽𝗹𝗼𝘆𝗺𝗲𝗻𝘁 𝗧𝘆𝗽𝗲𝘀 👇 It’s no secret that an AI Agent is a piece of software wrapping an LLM or multiple LLMs as a reasoning engine to guide its execution flow. The deployment types for these agents also closely resemble those of software or…
“No Way, MCP? By Anthropic?” I couldn't believe it when Anthropic announced it. Master Control Program? The all-powerful AI villain from Tron? LOL! Half shock, half irony. A company built to prevent runaway AI just named its protocol after the ultimate runaway AI? The perfect…
𝗔𝗜 𝗔𝗴𝗲𝗻𝘁’𝘀 𝗠𝗲𝗺𝗼𝗿𝘆 is the most important piece of 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗘𝗻𝗴𝗶𝗻𝗲𝗲𝗿𝗶𝗻𝗴, this is how we define it 👇 In general, the memory for an agent is something that we provide via context in the prompt passed to LLM that helps the agent to better plan and…
💥 New Course: Jupyter AI: AI Coding in Notebooks. Taught by @AndrewYNg and Brian Granger (@ellisonbg), co-founder of @ProjectJupyter. Coding assistants are transforming how we build software—but few work well inside notebook environments. Jupyter AI changes that. In this…
Memory in AI agents seems like a logical next step after RAG evolved to agentic RAG. RAG: one-shot read-only Agentic RAG: read-only via tool calls Memory in AI agents: read-and-write via tool calls Obviously, it's a little more complex than this. I make my case here:…
You're in an ML Engineer interview at Microsoft. The interviewer asks: "Why Boosting models primarily use Trees as the base learner? What's wrong with Linear regression or SVMs?" You: "Because linear models can’t fit non-linear data." Interview over. Here's what you missed:…
✨ LangChain Education Series: Post 1 In this post, I will show how to build your first SQL Agent fast using @LangChainAI. A step by step guide 🧵 👇
United States เทรนด์
- 1. Eagles 171K posts
- 2. Goff 18.8K posts
- 3. Lions 80.3K posts
- 4. Dan Campbell 9,476 posts
- 5. Gibbs 7,515 posts
- 6. Chiefs 92.6K posts
- 7. Jalen 32.4K posts
- 8. Nakobe Dean 2,082 posts
- 9. #OnePride 5,185 posts
- 10. #ITWelcomeToDerry 8,339 posts
- 11. Kevin Patullo 5,838 posts
- 12. AJ Brown 8,008 posts
- 13. Collinsworth 2,858 posts
- 14. Adoree Jackson 2,605 posts
- 15. NFC North 5,591 posts
- 16. GM CT 19.6K posts
- 17. Vic Fangio 3,072 posts
- 18. Shedeur 56.2K posts
- 19. #BaddiesUSA 11.1K posts
- 20. Jamo 4,721 posts
Something went wrong.
Something went wrong.