profile

The LLM Edge

πŸ—πŸš’πŸš€ smol agents --> DeepResearch

Published 3 months agoΒ β€’Β 2 min read

​

Hey, AIM community!

​

Next Wednesday, join us to tackle DeepSeek-R1! We'll also train our own reasoning model with Unsloth while we're at it! Additionally, we'll dig into what we know about how the model was trained, and how it was used to distill Qwen and Llama models.

​

Last week, we explored Hugging Face's smolagents library and we went Deep on their new open-source DeepResearch implementation. What makes the library "smol?" How is it better than competitors? How did the HF team recreate OpenAI's Deep Research tool within days? We covered it all, from concepts to code!

🧰 Resources

πŸ”­ Coming Up!

COCONUT: Chain of Continuous Thought

Reasoning means doing things for a reason; thinking them through, step-by-step. Running different Chains of Thought (CoT) is a critial part of this process. Exactly how we create and leverage these CoTs can differ, and COCONUT leverages latent space.

Cursor: An AI Engineer’s Guide

Want to become an AI Engineer or leader? Start here to learn to build, ship, and share with a best-practice stack, including Cursor, uv, Chainlit, Docker, Hugging Face, and OpenAI. The Cursor of today is the start of the engineer of the future. Check it out.

🌐 Around the Community!

πŸ’‘ Transformation Spotlight: Akash Shetty! Learn how he went from generic software developer to full-stack engineer who has just launched an AI-poweredGovTech startup. Read more about his story.

video preview​

πŸ€“ See what the community is building, shipping, and sharing this week. Join us in the Lounge every Monday at 9 AM PT for some accountability!

​

Want to join the AIM community? Hop into Discord and share your intro!

​

πŸ–ΌοΈ Meme of the Week

🌟 Want to start building, shipping, and sharing, but not sure how? Check out our LLM Foundations - a 5-day email-based course.

​

Keep building πŸ—οΈ shipping 🚒 and sharing πŸš€,

​

​Dr. Greg, The Wiz, Seraacha, and Lusk​
​AI Makerspace​

​
​Unsubscribe Β· Preferences​

The LLM Edge

Weekly Concepts, Code, and Community! Every Saturday you'll receive a detailed overview of one the latest tools or techniques from the open-source LLM edge.

Read more from The LLM Edge
The Llama 4 Herd

Hey, AI Makerspace community! This Wednesday, we'll cover the new release from OpenAI: Codex CLI, a lightweight coding agent that runs in your terminal. Carrying the same name as the original Codex models released in 2021, this new open-source tooling is a CLI-based coding agent that bears little resemblance to the model that originally powered GitHub Copilot. Join us to understand coding agents and best practices for their use in 2025 πŸ” Coming Up: What is an Agent? OpenAI just released their...

6 days agoΒ β€’Β 1 min read
RAG: The 2025 Best Practice Stack

Hey, AIM community! Tomorrow, we'll cover Enterprise Agents with OpenAI! What does the agents SDK look like from OpenAI? How does it build on previous work they've done? Are they officially in the end-to-end platform game competing with orchestration frameworks like LangChain, LlamaIndex, CrewAI, and others? Join us live to find out! Last week, we discussed RAG: The 2025 Best-Practice Stack This is the year of Practical RAG, and we kicked it off by unpacking the Minimum Viable...

26 days agoΒ β€’Β 2 min read
DeepSeek Week

Hey, AIM community! On Wednesday, we'll cover the infra stack that we recommend for RAG in 2025. Then, we'll build, ship, and share a best-practice RAG app. We'll also discuss important production tradeoffs and implications that you should consider before and after deployment when going from zero to production RAG! Last week, we discussed the latest open-source repo drops from DeepSeek Week, and we covered how they're being used as a new best-practice way to do inference on MoE models via...

about 1 month agoΒ β€’Β 2 min read