Hey, AIM community!

Join Dr. Greg and The Wiz as they cover Large Reasoning Models next Wednesday, Jan 18. With the release of o1, o3, and the new Gemini, everyone is talking about Chain-of-Thought Reasoning and Test-Time Compute. What are these things, anyway?

And what are the implications for building production LLM applications with models like this in 2025 and beyond? Join the discussion live on Wed. at 10 AM PT!

Last week, we dove into the latest RAG Evaluation metrics and RAGAS framework updates for building, shipping, and sharing production RAG applications in 2025!

🧰 Resources

🧑‍🏫 Concepts: Slides
🧑‍💻 Code: Evaluating RAG with Ragas (2025)
📜 Docs: Overview of Metrics and Design Principles

How do you focus on what matters in your RAG applications?

🔭 Coming Up!

Agent Evaluation with RAGAS

From RAG to Agents with RAGAS - it is 2025 after all! There are some interesting new metrics for assessing how agents use tools to solve problems. How can you ensure that your apps stay focused on the topic at hand while calling the right tools to achieve the goal? Find out live with us!

RSVP

Multimodality with Llama 3.2

Llama 3.2, Meta's first multimodal model, combines vision and text to tackle tasks like image captioning and document understanding. See how these models differ from text-only LLMs, from training to application. Learn how to harness Llama 3.2 for your workflows and projects.

RSVP

🌐 Around the Community!

💡 Transformation Spotlight: Vincent Kienzler, entrepreneur, CTO, and venture builder, has significant experience building companies, technical teams, and developing gen AI applications. Learn more about his journey!

🤓 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!

🪄 The Wiz dropped a test-time compute LinkedIn post series!
@AI_by_AI dropped the Virtual Contract Review & sports announcer avatar POC.
@Smail AI tells us why he charged $62,000 for a three-phase AI project.
@MikeC has assembled a mega list of 2025 AI conferences, hackathons, and meetups and has you covered for Week 3!
@Quentin Reul dropped a new pod on building ethical solutions.
@Nicolay talked about the black box of AI-powered search.
@Sahar dockerized and ran a research rabbit.
@AiMan1993 did some fine-tuning on ModernBERT.

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

AIE Cohort 5 Starts Jan. 14!

A few days remain to apply, complete the challenge, and grab a spot! Check out the schedule to learn more!

🖼️ Meme of the Week

🌟 Want to start building, shipping, and sharing but unsure how to begin? Check out our LLM Foundations - a 5-day email-based course to help you understand the inside of LLMs.

Keep building 🏗️ shipping 🚢 and sharing 🚀,

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