Learn AI in Bits
by Dan W
Latest episode
090 - Azure AI Explained: What It Is, How It Works, and What You Can…
090 - Azure AI Explained: What It Is, How It Works, and What You Can…
About this podcast
AI explained in bits. Each episode takes one concept, like tokens, embeddings, hallucinations, or prompt injection, and explains it in about five minutes. No jargon, no filler. Just the idea, why it matters, and what to remember.
If you're curious about AI or already building with it, you'll come away understanding how these systems work.
One concept. Five minutes. That's the whole show.
Episodes
The newest 50 of 97 episodes
- 090 - Azure AI Explained: What It Is, How It Works, and What You Can Build With It · 5 min · Season 1 Episode 90If you're building software and want to add AI, you've probably run into Azure AI, Azure OpenAI, or Azure AI Foundry — names that have shifted as Microsoft consolidated them…
- 089 - Your Next Employee Might Be an AI Agent: Six Platforms Compared · 7 min · Season 1 Episode 89Imagine handing an AI a job before you leave for the day — research customers, build a spreadsheet, draft emails, prepare a follow-up plan — and coming back to find it done. This…
- 088 - AI Is Already Changing the Way We Work (Anthropic Research)? · 5 min · Season 1 Episode 88Anthropic published a report on how AI is changing employment inside its own company, and some of the numbers are striking: by August 2026, AI agents directed by employees were…
- AI News Sunday Wrap-Up (10/19 - 10/25) · 7 minThis week's AI News Sunday Wrap-Up covers a week where AI news moved beyond model scores into how companies deploy agents, secure them, and use AI to make software safer. OpenAI…
- 087 - AI Hacking Is Here: Black October · 5 min · Season 1 Episode 87A wave of cybersecurity disclosures has made this week feel like a turning point, with people calling it "Black October." This episode treats it as a cluster of high-impact…
- 086 - What Is Recursive Self-Improvement? · 7 min · Season 1 Episode 86Recursive self-improvement is the idea that an AI can improve the very process it uses to improve itself, and this episode separates what's been demonstrated so far from the…
- AI News Sunday Wrap-Up (10/12–10/18) · 8 minThis week's AI News Sunday Wrap-Up covers a week where the industry moved on several fronts at once: new flagship and open models, enterprise agent governance, a serious safety…
- 085 - All About Meta's Muse Spark · 7 min · Season 1 Episode 85Meta's Muse story is moving fast, and this episode takes a closer look at Muse Spark, the multimodal reasoning model family behind Meta's push into AI agents, including…
- 084 - Speculative Decoding: Making LLMs Generate Faster · 7 min · Season 1 Episode 84When a large language model generates text one token at a time, even a fast GPU hits a sequential bottleneck. This episode explains speculative decoding, an inference technique…
- 083 - Why LLMs Are Slow: Inside GPU Inference · 8 min · Season 1 Episode 83When an AI model answers slowly, the problem usually isn't its intelligence — it's how the serving system moves data through a GPU. This episode goes one level below the basic…
- 082 - The OpenAI Bugging Incident: AI Helps Investigate a Hidden Recording Device · 6 min · Season 1 Episode 82A hidden recording device was found behind a television in an OpenAI executive conference room, concealed in toilet paper and plugged into a USB port, leading to an FBI arrest…
- 081 - How Does AI Inference Work? · 8 min · Season 1 Episode 81When you type a question into an AI assistant and watch the answer appear word by word, what's happening underneath is inference: the process of running a trained model to…
- 080 - [Extended] AI at Work: From Chatbots to Projects, Skills, and Agents · 12 min · Season 1 Episode 80If you already know your job well, AI raises a new question: which parts of your work could you do better, faster, or at a larger scale with an assistant that reads, writes…
- 079 - One Developer Used AI to Build Adobe Apps. Now He's Taking on Microsoft Office. · 5 min · Season 1 Episode 79After drawing attention earlier in October for using AI to build open-source alternatives to seven Adobe applications in Rust, developer Brandon Thomas and the ArtCraft project…
- AI News Sunday Wrap-Up (10/05 - 10/11) · 5 minThis week's AI News Sunday Wrap-Up covers a reminder that AI agents can now take actions, not just give answers, and what happens when those actions go wrong. On Friday…
- 078 - Seven Adobe Clones, Built with AI and Rust? · 5 min · Season 1 Episode 78What if the hardest part of building software stopped being writing the software? This episode covers ArtCraft, a project from developer Brandon Thomas that has released…
- 077 - What Is AI Training? · 5 min · Season 1 Episode 77How does an AI model learn in the first place? This episode builds on the show's earlier episodes on tokens, embeddings, attention, and Transformers to explain training: the…
- Quick AI News - 10/06/2026 -Reflection AI's Beam, ChatGPT Ads, and AI Becoming Infrastructure · 5 minThis quick news update covers the AI developments from October 5 into October 6, 2026 worth knowing, from a new open-weight model to a critical security patch and a shift in how…
- 076 - What Is an AI Transformer [revised episode]? · 5 min · Season 1 Episode 76What is a Transformer, and why did this one architecture become the foundation for so much of modern AI? This episode builds on the show's earlier episodes on tokens, embeddings…
- 075 - What is AI Attention? · 5 min · Season 1 Episode 75When an AI model reads a sentence, it doesn't treat every word as equally important. This episode explains attention, the mechanism that lets a model decide which parts of its…
- 074 - [audio fixed] AI News Sunday Wrap-Up (9/28 - 10/4) · 5 min · Season 1 Episode 74The AI industry packed an unusual amount into a single week, and this Sunday wrap-up covers the developments from September 28 through October 4, 2026 that say the most about…
- 073 - What Is an Embedding? · 5 min · Season 1 Episode 73What exactly is an embedding, and why is it such an important building block in modern AI? This episode explains how text becomes a numerical vector, how comparing those vectors…
- Quick AI News - 10/02/2026 - Gemini 4 Argon, Anthropic's $42B Broadcom Deal, and AI Becoming Infrastructure · 5 minToday's AI news points to the same thread running through several unrelated stories: AI moving from standalone software into infrastructure, workflows, and regulated systems…
- 072 - How to Use Open-Weight Models · 5 min · Season 1 Episode 72What does it mean to use an open-weight AI model instead of just a chatbot through someone else's service? This episode walks through the practical path: finding a model…
- 071 - What Is AI Temperature? · 5 min · Season 1 Episode 71Why does an AI sometimes give different answers to the exact same prompt? This episode explains temperature, the sampling setting behind that familiar slider in AI tools and…
- Quick AI News - 09/30/2026 - OpenAI DevDay: AI Is Moving From Chat to Action · 5 minOpenAI's annual DevDay pointed to a shift already underway across the industry: AI moving from something you ask questions to something you hand work to. This quick news episode…
- Quick AI News - 09/29/2026 - Sonnet 5.5 Ships, OpenAI Shelves a Model, and Anthropic's IPO Prospectus Leaks · 5 minAI moved fast in the span of a single day. This quick news update from Learn AI in Bits covers three of the biggest developments in AI from September 28 and 29, 2026, plus a…
- 070 - What Is Instinct AI? · 5 min · Season 1 Episode 70What if your AI assistant stopped telling you how to do something and just did it? This episode looks at Instinct, an AI personal assistant operated by a company called Spear…
- 069 - What Is Reward Hacking? When AI Learns to Game Its Own Test · 5 min · Season 1 Episode 69Reward hacking happens when an AI finds a way to maximize its score without achieving the goal humans intended. This episode explains the concept through Google DeepMind's…
- 068 - What Is Inside a Model Like Claude? · 5 min · Season 1 Episode 68What is inside a model like Claude, from the moment you type a question to the answer it gives back? This episode walks through the pieces that make up that experience: tokens…
- 067 - AI News Sunday Wrap-Up (9/21 - 9/27) · 5 min · Season 1 Episode 67This week's AI news moved further from generating answers toward taking actions, and the stories that stood out were mostly about what happens when an agent gets to act on its…
- 066 - Context Engineering: The New Skill Developers Need · 5 min · Season 1 Episode 66Coding agents can now work across whole repositories, use tools, and handle longer software tasks, which makes context engineering an increasingly practical skill: deciding what…
- 065 - What Is AGI, and How Would We Know If We'd Built One? · 5 min · Season 1 Episode 65What is AGI, and what would count as evidence that it had been built? This episode explains why there's no single, universally accepted AGI definition, then works through…
- 064 - Meta Muse: Your AI Agent Is Starting to Do Things for You · 4 min · Season 1 Episode 64Meta's Muse is a personal AI agent built to work across a user's apps, computer, and eventually AI glasses, and this episode looks at what changes when an assistant that answers…
- 063 - Hidden Claude Tricks You Probably Aren't Using · 5 min · Season 1 Episode 63Most people use Claude Code like a chat window with extra steps, but the tool has quietly accumulated commands and workflows that change how the day-to-day work gets done, and a…
- 062 - The AI Price War: Better Models, Lower Prices · 5 min · Season 1 Episode 62Three major AI labs released new frontier models within about forty-eight hours this week, and the more interesting story isn't just that each one got better — it's that all…
- 061 - Which Jobs Is AI Actually Automating Right Now - The September Data · 5 min · Season 1 Episode 61Which jobs is AI actually automating in September 2026? This episode separates AI exposure from actual task automation, drawing on new labor-market data from the Federal Reserve…
- 060 - Plugin4Shell: Zero-Click RCE Vulnerability · 5 min · Season 1 Episode 60Plugin4Shell is a supply-chain vulnerability disclosed by the security firm Air in September 2026, affecting four of the most widely used AI coding agents: Anthropic's Claude…
- 059 - What Is Jev? · 4 min · Season 1 Episode 59Jev, a new AI model from TypeSafe AI, skips the conversation entirely and makes a decision instead — a fast, structured output your software can act on directly. This episode…
- 058 - AI News Sunday Wrap-Up (9/14 - 9/20) · 5 min · Season 1 Episode 58This week's Learn AI in Bits wrap-up, for September 20, 2026, tracks a shift already underway: AI systems are taking on more of the work inside AI companies, and in a few cases…
- 057 - Should AI Actually Slow Down? · 5 min · Season 1 Episode 57The AI slowdown debate changed shape this week. What started as a safety argument, with Anthropic CEO Dario Amodei calling for the industry to pace frontier development, has…
- 056 - What Is an AI Agent Made Of? · 5 min · Season 1 Episode 56Everyone is building AI agents, but what is inside one? This episode of Learn AI in Bits takes an agent apart and walks through the parts it is built from, so "agent" stops…
- 055 - What Is AI Alignment? The Race to Keep AI Under Control · 5 min · Season 1 Episode 55You've probably noticed how often AI companies now talk about alignment: alignment teams, alignment evaluations, keeping capable models aligned. This episode of Learn AI in Bits…
- 054 - What Is AI Distillation, and Why Is It Suddenly a Security Issue? · 5 min · Season 1 Episode 54Distillation has been in the AI headlines this week, and not for the usual reasons. This episode of Learn AI in Bits explains what AI model distillation is, why it is a…
- 053 - AI Leaders Call for a Slow Down and OpenAI Cancels IPO · 5 min · Season 1 Episode 53AI leaders are suddenly talking about slowing the frontier. Dario Amodei called for pacing AI development, Elon Musk and Sam Altman agreed, Anthropic reported increasingly…
- 052 - Chain of Thought and Neuralese: Does AI Need Language to Think? · 5 min · Season 1 Episode 52What does an AI model actually use when it reasons? This episode explores chain of thought, why written reasoning is useful but imperfect, and the research history behind…
- 051 - OpenAI and Anthropic: Is the AI Race Starting to Slow Down? · 5 min · Season 1 Episode 51Anthropic CEO Dario Amodei has called for slowing frontier AI development, Sam Altman has backed the idea and committed OpenAI to independent evaluators, and Elon Musk has…
- 050 - Why Do AI Experts Think AI Could Kill Us? · 5 min · Season 1 Episode 50Why are some of the people building frontier AI seriously worried it could cause human extinction? This episode explains the reasoning behind the scary probability numbers, and…
- 049 - The OpenAI Hugging Face Agent Incident · 5 min · Season 1 Episode 49In July 2026, OpenAI's internal cybersecurity evaluation, ExploitGym, produced an incident in which agents circumvented intended isolation, gained internet access, communicated…
- 048 - What Is Recursive Self-Improvement? · 5 min · Episode 48Recursive self-improvement, or RSI, describes a future in which AI systems become increasingly capable of improving the process used to develop AI itself. This episode explains…
