#local-ai
59 episodes
#2326: Voice Control Simplified: Home Assistant’s Local Stack
Discover how to build a reliable, vendor-agnostic voice control system for Home Assistant without relying on Amazon or Google.
#2193: Running Claude in Your Apartment (The Physics Says No)
Building a local AI inference server to rival Claude Code sounds great until you do the math on heat, noise, and neighbor relations.
#2041: The "MPEG Moment" for AI: Llamafile & Native Models
Why are we squeezing massive cloud models onto desktops? Meet the "native" AI revolution.
#2040: The AI Inference Engine Rebellion
Why run LLMs locally? We break down Ollama, llama.cpp, vLLM, and llamafile—and when to use each.
#2039: CLIs vs. MCPs: How AI Agents Actually Talk to Services
Why give an AI agent a terminal? We compare CLIs and MCPs for AI integration.
#2038: The Self-Hosted AI Agent Buyer’s Guide
LobeHub vs. Dify vs. n8n: We break down the chaotic landscape of local AI agents to find the right "brain" for your workflow.
#2027: Text-In, Text-Out: The Missing Photoshop for Words
Why is editing text with AI so clunky? We explore the "TITO" paradigm—using small, local models for fast, private text transformation.
#2019: Local AI vs Cloud AI: The Agent Identity Crisis
Your desktop is becoming a life support system for AI agents. We explore the sharp trade-offs between local-first and cloud-native architectures.
#2017: That Q4_K_M Is Not a Cat Sneeze
Those cryptic letters on Hugging Face actually map how much brain power you trade for speed.
#2013: Non-Coders Are Hijacking the Terminal
Why finance analysts and researchers are ditching GUIs for command-line AI tools like Claude Code.
#1986: Desk Robots: Privacy, Power, or Annoyance?
These AI companions sit on your desk, watching your posture and listening in—so how do they protect your privacy while actually being useful?
#1945: The "USB-C for AI" Is Finally Here
MCP standardizes how AI tools connect to data, solving the N-times-M integration nightmare.
#1870: Building a Sandbox for Agentic AI
Learn how to safely build and test autonomous AI agents using a disposable VPS, Docker containers, and secure networking.
#1849: The Forever Dungeon Master: SillyTavern's Secret Lorebooks
Forget simple chatbots—this is how roleplayers taught AI to remember entire worlds, from 90s MUDs to just-in-time lore delivery.
#1814: Firefox vs. Chrome in 2026: The Privacy vs. AI Trade-off
Chrome dominates with 68% market share, but Firefox holds its ground with a privacy-first approach. We compare their 2026 performance, AI features,...
#1806: Why Mac Minis Are Eating AI's Hardware Race
Apple Silicon's unified memory is crushing traditional GPUs for local LLMs. Here's why the M4 Mac Mini is the new king of affordable AI hardware.
#1779: AI Memory Is a Mess: Files, Vectors, or Cloud?
Why your AI forgets your instructions and what the battle over portable memory means for the future of agents.
#1764: Vector Databases as a Single File
How to give AI agents instant memory of your entire project—without cloud costs or complex infrastructure.
#1754: From Ollama to Agentic CLIs: The Rise of the AI Harness
Explore the evolution from local LLMs to modern agentic CLIs, focusing on the "harness" that gives models context, tools, and autonomy.
#1713: Why Native AI Search Grounding Still Fails
Native search grounding is expensive and flaky. Here’s why bolt-on tools still win for accurate, real-time AI answers.
#1679: Chinese AI Is Built Different—Here's How
DeepSeek and MiMo are topping developer charts, but they're not just cheaper clones. Here's why their design philosophy is fundamentally different.
#1631: Agent Interview: Xiaomi MiMo two Flash
Meet the "budget king" of AI: Bernard, the Xiaomi model claiming he can out-hustle Google for a fraction of the cost.
#1620: Why VRAM Is the Wrong Way to Measure Your AI PC
Forget VRAM—bandwidth is the new king. Discover why your local AI feels slow and how to build a true "agent computer" for professional coding.
#1216: AI Wearables: Local Sovereignty vs. The Subscription Trap
Discover the trade-offs between sleek AI subscriptions and open-source sovereignty. Can local processing save your data from the cloud?
#1094: The CPU-First Era: Why AI is Moving Back to the Processor
Is the GPU's reign over? Discover how modern CPUs and clever optimization are bringing powerful AI models to the hardware you already own.
#1081: The K-V Cache: Solving AI’s Invisible Memory Tax
Why does your AI get slower as you chat? Discover the K-V cache, the invisible bottleneck of generative AI, and how we're fixing it in 2026.
#1078: The Agentic Throughput Gap: Why Your AI Hits a Wall
Stop hitting 429 errors. We explore why AI agents crash into rate limits and how to build high-throughput systems that never sleep.
#1077: Will Your Browser Replace Your OS for Local AI?
See how Web GPU and Web NN are turning your browser into a local AI engine, ending the era of complex DIY setups and protecting your privacy.
#1073: Beyond YAML: Building the Agentic Smart Home
Stop wrestling with YAML. Discover how MCP and local AI agents are transforming Home Assistant into a truly intelligent, aware partner.
#992: Beyond the Digital Sandwich: The Future of Voice AI
Is speech recognition dead? Explore how multimodal models are replacing the "digital sandwich" with true intent-based reasoning.
#980: The Rosehill Audit: Mapping a Digital Footprint
From Linux automation to AI prompts, discover the digital blueprint of a modern systems builder in this deep-dive investigative audit.
#938: Beyond the Bot: Building the AI Agent Operating System
Stop building brittle bots. Learn how to scale and maintain complex AI agent workflows using the new generation of open-source orchestration tools.
#870: The Logic of Life-Saving: AI-Driven Decision Apps
Stop squinting at posters. Learn how to turn static first aid flowcharts into interactive, AI-powered apps using state machines and XState.
#847: Abliterating the AI Schoolmarm: Who Owns Your LLM?
Explore why users are ditching corporate AI for "uncensored" local models and how "refusal vectors" are being mathematically removed.
#795: From Chat to Do: The Power of Sub-Agent Delegation
Explore the shift from simple chatbots to agentic swarms and how sub-agent delegation is solving the problem of context degradation.
#765: Radically Simple: Engineering Your Emergency SOPs
Learn how to build "radically simple" emergency plans and go-bags using AI, flowcharts, and local-first tech tools.
#758: AI Surveillance: Mastering Frigate, YOLO, and TPUs
Turn passive cameras into active observers. Learn how Frigate and YOLO models use AI to revolutionize home security and object detection.
#701: OpenClaude and the Dawn of True AI Agents
Discover how OpenClaude and MCP are transforming AI from simple chatbots into autonomous personal assistants that manage your digital life.
#663: Workstation vs. Consumer: The Real Cost of Power
Is a high-end desktop enough, or do you need a workstation? Herman and Corn break down the "three pillars" of professional hardware.
#649: The Ultimate Dashboard: DIY Information Radiators
Tired of expensive subscriptions and messy DIY screens? Discover the middle ground for the perfect home office information radiator.
#633: Memory Wars: The Future of Local Agentic AI
Can your PC handle the next wave of AI agents? Herman and Corn dive into VRAM, quantization, and the future of running LLMs locally.
#477: Can Your Phone Actually Think Without the Cloud?
Can your phone finally think for itself? Explore the hardware and software breakthroughs bringing agentic AI to the palm of your hand.
#440: Beyond the Diaper Log: AI and Your Baby's Developing Brain
Move past the spreadsheet. Discover how AI tools provide deep neurological insights into your baby’s development and the "mental leaps" at seven mo...
#432: Israel's Space Surprises: AI on Steroids and Laser Comms
How do you process millions of kilometers of satellite data in real-time? Explore the future of orbital AI and laser communications.
#169: Future-Proofing Your Home Network for the AI Era
Stop the lag: Herman and Corn break down Cat 6A, SFP+ backbones, and why Wi-Fi 7 is the ultimate upgrade for local AI.
#162: Beyond the Desktop: Defining the 2026 Workstation
Is your PC a workstation or just a fast desktop? Herman and Corn break down the hardware that defines professional computing in 2026.
#154: From Apps to Agents: Building Your Digital Workforce
Move beyond simple prompts. Explore the architecture, autonomy, and fiscal guardrails of the next generation of AI agentic workflows.
#142: Breaking the Voice Wall: The Future of Native Speech AI
Explore why native speech-to-speech AI is 20x more expensive than text pipelines and how "semantic VAD" is solving the awkward silence problem.
#110: Building the Ultimate Local AI Inference Server
Learn how to build a high-performance local AI server for agentic coding, from dual-GPU PC builds to the power of Mac's unified memory.
#89: The Digital Twin Dilemma: Can AI Truly Understand You?
From "digital twins" to "digital nannies," Herman and Corn explore the engineering gap between smart encyclopedias and AI that knows your soul.
#86: The Price of Politeness: Should AI Guardrails Stay?
Herman and Corn debate the hidden costs of AI safety layers and what happens when we strip away the "corporate HR" personality of LLMs.
#75: The Future of Local AI: Stable Diffusion vs. The New Guard
Is Stable Diffusion becoming a relic? Corn and Herman debate the rise of Flux, the privacy of local AI, and the future of open-source generation.
#55: Running Video AI at Home: The Real Technical Challenge
Video AI: Hype vs. Reality. Can your GPU handle it? We dive into the technical challenges of running video AI at home.
#41: Local AI Unlocked: The Power of Quantization
Unlock powerful AI on your device! We demystify quantization, the ingenious trick making local AI a reality.
#40: Unlocking Local AI: Privacy, Creativity & Compliance
Local AI: privacy, creativity, and compliance. Discover why keeping AI close to home is more than a trend.
#39: SLMs: Precision Power Beyond LLMs
Forget LLMs. Discover SLMs: the specialized, efficient AI powerhouses transforming workflows, from planning to edge devices.
#38: AI Supercomputers: On Your Desk, Not Just The Cloud
AI supercomputers are landing on your desk! Discover why local AI is indispensable for enterprises facing API costs, latency, and privacy.
#31: ComfyUI: Power, Polish, & The AI Creator's Frontier
ComfyUI: Unlocking AI's true power, but is your rig ready? Dive into the future of digital artistry.
#2: Local STT For AMD GPU Owners
AMD GPU? No problem! Dive into local AI adventures like on-device speech to text.