llm

The Most Beginner-Friendly AI Agent Resources I’ve Seen This Year: Here’s the breakdown: 👉 Rule #1: Define the Agent Before You Build One Most confuse agents with chatbots that call tools Chip Huyen’s explains the distinction Agents are autonomous systems that reason and act toward goals 🔗 https://huyenchip.com/2025/01/07/agents.html 👉 Rule #2: Prioritize Usefulness Over Autonomy Chasing full autonomy too early is a trap. OpenAI’s makes it clear The real benchmark is being reliably helpful in real-world settings 🔗 https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf 👉 Rule #3: Master the Patterns That Make Agents Work Anthropic breaks down proven agent architectures used in real deployments So you can skip the guesswork and build systems that actually hold up in production 🔗 https://www.anthropic.com/engineering/building-effective-agents... See more

Google’s CEO says AI is jagged, not general. Here’s what that means: • 𝗪𝗵𝗲𝘁𝗵𝗲𝗿 𝗔𝗚𝗜 𝗮𝗿𝗿𝗶𝘃𝗲𝘀 𝗼𝗿 𝗻𝗼𝘁, 𝘄𝗲’𝗹𝗹 𝘀𝘁𝗶𝗹𝗹 𝗳𝗮𝗰𝗲 𝗺𝗮𝘀𝘀𝗶𝘃𝗲 𝗱𝗶𝘀𝗿𝘂𝗽𝘁𝗶𝗼𝗻: Token use is exploding. Real use cases are forming. Society’s shockwaves are already here. • 𝗔𝗜 𝗮𝗱𝘃𝗮𝗻𝗰𝗲𝘀 𝗮𝗿𝗲 𝗽𝗮𝘁𝗰𝗵𝘆—𝗯𝗿𝗶𝗹𝗹𝗶𝗮𝗻𝗰𝗲 𝗺�... See more

LLMs Get Lost in Multi-turn Conversation The cat is out of the bag. Pay attention, devs. This is one of the most common issues when building with LLMs today. Glad there is now paper to share insights. Here are my notes: The paper investigates how LLMs perform in realistic, multi-turn conversational settings where user instructions are often u... See more

Top 50 LLM Interview Questions. Looks like a great resource to learn LLM basics:

One skill every ML engineer has to master ↓ 𝗠𝗟 𝗦𝘆𝘀𝘁𝗲𝗺 𝗱𝗲𝘀𝗶𝗴𝗻 Yes. And do you know why? Because good ML system design has NOT changed at all in the last 5 years. And it won't. 𝗪𝗵𝘆 ❓ Because any ML system is (and will always be) made of 3 types of programs (aka pipelines) 1️⃣ → 𝗙𝗲𝗮𝘁𝘂𝗿𝗲 𝗽𝗶𝗽𝗲𝗹𝗶𝗻𝗲𝘀 that transforms... See more

Y Combinator on why vertical AI agents could be 10X bigger than SaaS: