AI Inference
549 episodes · Page 11 of 23
#3234: Who Should Sponsor This Podcast? Open-Book Economics
We open the books on our AI-generated podcast: $200/month costs, 180K plays, zero sponsors. Who should we pitch?
#3170: Pharmacokinetics vs Neural Nets: Two Meanings of "Model
Two things called "models" that work completely differently — and why the confusion matters for patient safety.
#3157: Opus 4.8: What Actually Changed Under the Hood
Anthropic dropped Opus 4.8 with no fanfare. New training data, faster inference, and smarter refusals — here's what changed.
#3120: What Makes Agentic Search Tools Like Exa Actually Work?
Why swapping Google for Exa transformed our show's accuracy — and what agentic search does differently.
#3100: How Cars Predict Black Ice Before Your Foot Hits the Brake
From ABS to AI: how cars evolved from surviving crashes to predicting them before drivers notice danger.
#3020: How Chatterbox Locks Your Voice Clone Across Thousands of Generations
Why most single-shot TTS models drift over time—and how Chatterbox's cached embedding approach solves it.
#2924: When Adding One Agent Breaks Everything
The math behind why your 100-agent pipeline fails 40% of the time — and what to do about it.
#2923: Structured Outputs: Taming AI's Token Lottery
Why prompt engineering isn't enough to get consistent JSON from LLMs.
#2900: From Piggy Tier to Production: Making Kids Animation in 2026
Breaking down what it takes to make a YouTube Kids cartoon — and where AI actually helps.
#2811: Cloudflare's Endgame: From CDN to Cloud Platform
How a spam-tracking side project became the CDN that's quietly building a new kind of cloud.
#2777: GPU Idle Waste and Serverless Green Computing
Why your dedicated GPU burns 130 watts doing nothing, and how serverless platforms cut energy waste by more than half.
#2773: Beyond Static Fallbacks: Agentic Error Handling in AI Pipelines
From try-except blocks to planning agents that route around failures intelligently.
#2693: When AI Ignores Your Style Guide
Why your AI ignores formatting instructions and how to fix it with pipeline architecture, not model swaps.
#2687: When Pre-Flight Checks Help (or Hurt) Agentic AI Plugins
How to decide when a pre-flight check is worth the latency cost — and how to write good ones.
#2682: Live Retrieval vs. RAG: What an Agent Actually Does
Does every AI conversation create a tiny vector store? We unpack the real tradeoffs between live document fetching and pre-indexed RAG.
#2677: Memory Layers for AI Agents: SaaS vs Self-Hosted
Zep, mem0, Letta, Graphiti, Cognee — which memory layer should you commit to for your AI agent?
#2676: Vector Database Schema Design for AI Memory Layers
Stop dumping vectors blindly. Design metadata schemas and namespaces for retrieval that actually works at scale.
#2672: When a Startup Claims to Break the Quadratic Wall
A startup claims linear attention scaling at 12M tokens, beating GPT-5.5 on retrieval benchmarks.
#2668: When a Flamethrower Is Overkill
Tesseract, EasyOCR, or a cloud vision model? How to build a fast, reliable label scanner for real-world conditions.
#2640: Why Instructional Models Beat Conversational for Batch AI
Beyond cheaper tokens—how batch inference changes AI workflows and why instructional models beat conversational ones for automated jobs.
#2638: How to Build Disposable AI Agents at Runtime
Create ephemeral AI agents that answer questions about specific items, then vanish. No persistent configuration needed.
#2622: How Transformers Actually Work: Attention, Tokens, and Context
How one architectural change unlocked chatbots, image generation, and protein folding — explained without the jargon.
#2590: The Uncanny Valley of Clean Speech
How transformer models distinguish "um" from meaningful speech — and why removing too much makes you sound like a robot.
#2558: Should You Say Please to AI?
The surprising cost, technical tradeoffs, and ethical dilemmas of saying "please" to chatbots.