🏗️ 🚢 🚀 Reinforcement Learning with Verifiable Rewards
about 5 hours ago • 1 min readCOMING UP THIS WEEK How to Build ChatGPT - Part I: Prompting & Responses API We’re kicking off a new series: How to Build ChatGPT! 🚀 Step by step, we’ll cover everything from prompting and the Responses API to RAG, agents, reasoning, and full end-to-end application design—mirroring the journey that transformed ChatGPT from a simple front end into today’s powerful ecosystem. RSVP now to Part I: Prompting & Responses API and Part II: RAG and Connectors 🏗️🚢🚀. Part I: Prompting & Responses API...
READ POST🏗️ 🚢 🚀 AWS Agent Squad
7 days ago • 1 min readCOMING UP THIS WEEK Reinforcement Learning with Verifiable Rewards Join us for Reinforcement Learning with Verifiable Rewards. This new standard of RL is worth understanding today as an AI Engineer or LLM Engineering Practitioner. This session will get you up to speed on what makes RLVR different than previous methods we've studied before on our channel including RLHF, RLAIF, DPO, and others. We'll compare and contrast RLVR and GRPO (popularized by DeepSeek-R1) and build, ship, and share some...
READ POSTContext Engineering for Agents
15 days ago • 3 min readAn Introduction to Context Engineering According to @dexhorthy, "everything that makes agents good is context engineering." Check out his talk from the AI Engineer World's Fair from June 3, 2025. Image Credit: Dex Horthy We agree. You shall know a word by the company it keeps. ~ John Firth, A Synopsis of Linguistic Theory (1957) Today, we might say: You shall know an LLM application (or agent) by the context it keeps ~ AI Makerspace We were pumped to see Dex - the man who coined the phrase -...
READ POST🏗️ 🚢 🚀 Arcee AI's AFM-4.5B & Typedef's Fenic
21 days ago • 1 min readCOMING UP THIS WEEK gpt-oss: The Frontier of Open-Weight Reasoning Models OpenAI just dropped gpt-oss, their first open-weight LLM since GPT-2. In this session, we'll unpack what’s inside the 120B and 20B variants: agent-friendly tool use and CoT strengths, long-context (128k), MoE FFNs, GQA, the SFT+RL training pipeline, and the safety work behind the release (including the new risk-assessment paper). We’ll also cover the tokenizer/prompting stack (o200k_harmony + harmony format), compare...
READ POST🏗️ 🚢 🚀 Guardrails AI
about 1 month ago • 1 min readEVENT RECAP Guardrails Last week, we were joined by the co-founders of Guardrails AI to unpack guardrails for LLM applications: what they are, why they are important, and how to thread them through the AI lifecycle. Guided by the AI Guardrails Index, we explored techniques to handle jailbreak protection, PII stripping, and hallucination suppression. 🧑🏫 Slides 🧑💻 Code 🎥 Recording COMING UP THIS WEEK AFM: Arcee Foundation Model Arcee AI just dropped AFM-4.5B—another Small Language Model (SLM)...
READ POST🏗️ 🚢 🚀 Context Engineering
about 1 month ago • 3 min readTwo years ago, AI Makerspace opened its digital doors with a bold vision: to build the world's leading community for people who want to build, ship, and share production-grade LLM applications. Today, that spark has erupted into a global learning community that is shipping and sharing prototypes on a daily basis. In just 24 months, we’ve launched 13 cohorts, served over 450 students, of which 137 are now certified AI engineers. Keep building, shipping, and sharing with us, like legends 🏗🚢🚀....
READ POST🏗️ 🚢 🚀 Large Reasoning Models: The Illusion of Thinking
about 2 months ago • 2 min readEVENT RECAP 🧠 The Illusion of Thinking Last week, we examined The Illusion of Thinking, which argues that scaling up test-time compute does not work on problems of extremely high complexity. The response paper by Claude Opus, et al. "The Illusion of The Illusion of Thinking" argues the paper was contrived and poorly designed. Who is right, and wait, do LLMs think or not?? 🧑🏫 Slides 🎥 Recording COMING UP THIS WEEK Deep Research: The API OpenAI has officially released Deep Research through the...
READ POST