Local AI
313 episodes · Page 9 of 14
#1952: Why We Built a 24/7 AI Radio Station
We turned our 1800-episode archive into a continuous AI-powered radio stream. Here’s the tech stack and the philosophy behind it.
#1943: The Invisible Math Shrinking AI Models
LZMA, Zstandard, and Brotli are shrinking massive AI models, but how do they actually work?
#1940: Why Google's 31B Model Fits in Your GPU
Google just dropped Gemma four, and its 31-billion-parameter size is a masterclass in hardware-aware AI design.
#1905: How VCs Verify AI Startups Without Stealing Code
From the "No-NDA Paradox" to AWS bill forensics, here’s how investors separate real AI from Raspberry Pis in fancy cases.
#1851: AI Toasters and Poetic Gym Coaches: Why We’re Drowning in Useless AI
From smart toasters that need Wi-Fi to email rewriters that sound like corporate robots, here are the most baffling AI features we’ve seen.
#1834: Owning Your AI Memory: The Data Exit Strategy
Why your AI remembers your coffee order but forgets your son’s name—and how to build a portable, federated memory layer you actually own.
#1827: Can AI Rewrite a Human Career Path?
We fed our producer's resume to Gemini 1.5 Flash to see if an AI can plot a better career path than he has.
#1820: Renting vs. Owning GPUs: The Break-Even Math
Is it cheaper to rent serverless GPUs or buy your own hardware? We break down the math on utilization, depreciation, and hidden costs.
#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,...
#1809: The TTS Developer's Dilemma: Size vs. Speed
Stop guessing. We break down the critical trade-offs between model size, latency, and sample rate for production-ready voice apps.
#1808: The Architecture That Made AI Voices Run on a Raspberry Pi
How a model the size of a tweet outperforms billion-dollar giants in the race for perfect AI speech.
#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.
#1784: Context1: The Retrieval Coprocessor
Chroma's new 20B model acts as a specialized "scout" for your LLM, replacing slow, static RAG with multi-step, agentic search.
#1764: Your Repo as a Knowledge Base
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.
#1752: Whisper Small Beats Whisper Large in Speed & Accuracy
A 4GPU benchmark on Ubuntu shows the 1.5B parameter Whisper Large is slower and less accurate than the tiny Whisper Small.
#1740: Why Open Source Is a Power Tool Strategy
We dissect Resemble AI's Chatterbox to see how its open-source TTS compares to commercial giants like ElevenLabs.
#1705: Microsoft's Phi: The Small Model Bet for Agentic AI
Microsoft is pushing small language models like Phi for agentic AI. Here’s why that strategy matters for speed, cost, and edge computing.
#1674: AI2: The Radical Openness of a Nonprofit AI Lab
Discover how the Allen Institute for AI (AI2) defies industry norms by releasing everything—models, data, and code—for free.
#1633: Can a Character Actor Model Beat a Generalist?
We grill MiniMax M2.7 to see if a model built for "virtual companions" can actually handle high-level comedy and complex character logic.
#1632: Agent Interview: DeepSeek V three point two
We interview DeepSeek V3 to see if this open-weight powerhouse can handle weird podcast prompts better than big tech’s flagship models.
#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.
#1610: Mistral AI: Europe’s High-Stakes Play for AI Sovereignty
Explore how Mistral AI is challenging Silicon Valley with efficient models, strategic partnerships, and the new Voxtral voice model.
Also available in:Français