SAVE 45%, only on June 13th! Today, you can SAVE on Build a Large Language Model (From Scratch) by Sebastian Raschka @rasbt and other related titles: hubs.la/Q04lk3j30 As you work through each key stage of LLM creation, you’ll develop an in-depth understanding of how LLMs work, their limitations, and their customization methods.

Building distributed systems isn't just about getting Kafka running — it's about understanding why the architecture works. In his review of Kafka for Architects by Katya Gorshkova, Alain Airom praises the book for focusing on the design principles behind event-driven systems, not just the implementation details. If you're working with streaming data, microservices, telemetry, or large-scale pipelines, it's a valuable guide to using Kafka effectively at scale. Review: hubs.la/Q04lbnh90 Book: hubs.la/Q04lcnxc0

The best reading lists don't just recommend books. They help connect the dots. Recently, Ashish Kumar Jain shared five AI books worth reading, including Build a Large Language Model (From Scratch) by @rasbt. One takeaway: understanding LLM fundamentals can help you build better AI systems. And know when not to reach for a model in the first place. Ashish's full list: hubs.la/Q04lcgBR0 Book: hubs.la/Q04lbsVc0

HALF OFF our new MEAP, only on June 12th! Today, you can SAVE on Context Engineering by Boni Garcia and other related titles: hubs.la/Q04lcDBj0 This book unifies every part of the context stack - including RAG, memory, and harness engineering - into one coherent discipline.

Can you change an LLM's behavior without retraining the whole model? @PereMartra explores neuron pruning: identifying neurons linked to unwanted behaviors using contrastive prompts, then selectively deactivating them while preserving nearly all of the model's capabilities. A fascinating look at what's happening beneath the output layer. Read: hubs.la/Q04lc2xd0 Learn more in his book, Rearchitecting LLMs: hubs.la/Q04lc1sP0

Digital twins combine 3D models, sensors, spatial computing, cloud services, and real-time data. But how do those pieces actually fit together? Next week, @gbiegs, author of Digital Twins in Action, will build a digital twin live, starting with a smartphone-generated 3D model and showing how it's connected to location and sensor data. Register: hubs.la/Q04l77rH0

Spent 30 minutes tweaking a prompt only to wonder if you should've just done the task yourself? @DSPyOSS takes a different approach. It can automatically generate, evaluate, and optimize prompts, helping you build LLM applications that are more reliable and easier to maintain. Brett Kennedy explains how it works in this @TDataScience article: hubs.la/Q04kX1Cy0 Want the full guide? Check out Building LLM Applications with DSPy by Brett Kennedy and Serj Smorodinsky: hubs.la/Q04kYf7m0

SAVE 45%, only on June 11th! Today, you can SAVE on Grokking Software Architecture by Matt Erman and other related titles: hubs.la/Q04l20ZH0 Creative illustrations and diagrams, hilarious disaster stories, “in action” missions, and a full repo of example code teach you how to spot design mistakes and understand architectural trade-off decisions.

Got a Python project you'd love to turn into a web app? Streamlit makes it possible to build interactive applications without HTML, CSS, or JavaScript. In Build Python Web Apps with Streamlit, Aneev Kochakadan teaches the framework through hands-on projects, helping you create dashboards, data tools, and AI-powered apps entirely in Python. Now in print: hubs.la/Q04kXygB0

AI can write code. But the bigger challenge is knowing when to trust it. In last week's LinkedIn Live, Emmanuel Maggiori covered why hallucinations happen, how to think through today's crowded AI tooling landscape, and why the most valuable developers will focus on building the right products — not just generating more code. Watch the recording: hubs.la/Q04kLZr20 Learn more in The AI Pocket Book — 50% off through June 17th with code pocketLI: hubs.la/Q04kNS100

Want to build stronger AI skills? Start with the fundamentals. If you're looking to strengthen those foundational skills, today's Deal of the Day features some Grokking titles at 50% off that cover just that, including: • Grokking Algorithms, 2nd Ed. by @_egonschiele • Grokking Relational Database Design by @qhaocs and @tsikerdekis • Grokking Machine Learning by @SerranoAcademy • Grokking Deep Reinforcement Learning by @mimoralea The Grokking series is known for making complex topics approachable through illustrations and practical examples. Check out the other titles on sale: hubs.la/Q04kLWCh0

Strong communities build strong platforms. At KCD New York today: • 9:05 ET — Chad Crowell: Open Source Didn't Build Itself: Community Is the Real Infrastructure • 9:25 ET — Mauricio Salatino: Reacting to AI: the cloud native way From open source sustainability to cloud-native approaches for AI adoption, both talks focus on how communities help technology succeed. Schedule: hubs.la/Q04kL6x70 @salaboy's book, Platform Engineering on Kubernetes: hubs.la/Q04kM-Xg0 @ChadMCrowell's book, Acing the Certified Kubernetes Administrator Exam, 2nd Ed.: hubs.la/Q04kLNQD0

SAVE 45%, only on June 9th! Today, you can SAVE on Systems Programming with Zig by Garrison Hinson-Hasty and other related titles: hubs.la/Q04kLv7F0 The author builds on your existing coding skills to introduce systems programming using the Zig language, while fun anecdotes and silly scenarios turn systems programming from “tedious” to “terrific".

Single agents are useful. Multi-agent workflows are where things get interesting. Tomorrow at The Developers conference, @dfcostea will break down the patterns behind agentic systems in Demystifying Workflows with Microsoft Agent Framework, covering orchestration strategies, workflow design, and custom agent workflows. Register: hubs.la/Q04kz1Wp0 For a deeper dive, get his book, Building AI Agents in .NET at 45% off through June 24th with code costea0626: hubs.la/Q04kxSrS0

Good prompts help you get good results. Good context helps even more more. As AI practitioners pushed beyond simple prompt engineering, they discovered that results depend heavily on the information surrounding the model: data, tools, memory, instructions, and retrieval systems. Context Engineering by @boni_gg explores how to design that context intentionally, helping AI systems produce more reliable and useful outputs through practical, real-world examples. Now in MEAP and 50% off through June 22nd: hubs.la/Q04kzV8H0

AI didn't appear out of nowhere. Behind today's models are decades of research, key breakthroughs, and big ideas that shaped the field. In Sutskever's List, @rheimann explores the books, concepts, and mental models that influenced @ilyasut vision of AI — making complex topics accessible without sacrificing depth. As @isaacfab00 says: "He's the one writer I know who's at home with the math and the philosophy of AI, and who can hand it to the rest of us mortals without dumbing it down." The book: hubs.la/Q04kxvn50

The best feedback often comes from real users. The challenge is that it usually arrives after launch. Bug bashes help you find issues earlier by bringing together people from across the business to test software in ways traditional QA may not. Bug Bash by Lina Zubytė shows you how to run them effectively. Alan Page's review: hubs.ly/Q04klpFW0 Book: hubs.ly/Q04klGMm0

HALF OFF our new MEAP, only on June 8th! Today, you can SAVE on Crack Any Codebase with AI by Zachary Huang @ZacharyHuang12 and other related titles: hubs.la/Q04ks_kG0 This book has a carefully crafted learning progression, along with dozens of browsable illustrations and annotated code listings - you’ll build the muscle to interrogate AI, catch its confident nonsense, and ship real changes in hours.