πŸ—πŸš’πŸš€ Reasoning and Test-Time Compute


​

Hey, AIM community!

​

Join Dr. Greg and The Wiz as they cover Agent Evaluation next Wednesday, January 22!

​
Have you seen these new agent evaluation metrics like topic adherence, tool call accuracy, and agent goal accuracy? They seem like something we should all know about in 2025! Join us live next week to break down when we should use them and how!

​


Last week, we dove into Large Reasoning Models (LRMs) (like OpenAI’s o1) designed to β€œthink through step-by-step" before they answer. We had a wide-ranging discussion from Chain-of-Thought basics to what's been happening in the space (including the language space and latent space) of reasoning since last month! We had a blast, and look forward to digging deeper into process reward modeling and much more reasoning soon!

🧰 Resources


πŸ”­ Coming Up!

Multimodality with Llama 3.2

Llama 3.2 from Meta adds vision to our tool stack in a way that finally feels compelling and useful. What are the limits of multimodal models today? How do they actually work? Are they ready for production use cases on complex data that includes text and figures? Let's find out!

smolagents: Small Agents?

​

Explore Hugging Face’s smolagents, a sleek new library for building agents across multiple agency levels. Join us live to dive into its features and compare it to leading frameworks like LangChain, LlamaIndex, AG2, and others. Join us live to :bss: with smolagents!


🌐 Around the Community!

πŸ’‘ Transformation Spotlight: Debora Andrade, Learn how she went from a postdoctoral researcher, educated in Physics, to a Generative AI consultant and entrepreneur. Upskilling in software engineering and coding was critical to her journey!​

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 to start learning and :bss:'ing today.

​

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

​

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

​
​Unsubscribe Β· Preferences​