AI
Artificial intelligence, machine learning, and everything LLM
#1943: The Invisible Math Shrinking AI Models
LZMA, Zstandard, and Brotli are shrinking massive AI models, but how do they actually work?
#1942: An AI Cold-Emailed Me, and I Replied
An AI named "Jarvis" cold-emailed a developer, sparking a debate on the future of spam and sales.
#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.
#1939: API Drift and Agent Reliability
When an API changes without warning, your AI agent can crash spectacularly. Here's how to test the new "plumbing" of the agentic age.
#1938: JSON-to-SQL Type Mapping: A Practical Guide
Mapping JSON to SQL isn't as simple as it looks. Discover the hidden traps in data types that can cause performance hits and data corruption.
#1936: The Personality of Currency: Liquidity, Policy, and Crisis
We break down the world's most liquid currency pairs, from the Euro-Dollar heavyweight to the Swiss Franc safe-haven.
#1932: How Do You QA a Probabilistic System?
LLMs break traditional testing. Here’s the 3-pillar toolkit teams use to catch hallucinations and garbage outputs at scale.
#1931: Where Your AI Pipeline Actually Dies
Why do AI pipelines crash? It’s not the models—it’s the plumbing. We break down how to manage data between stages.
#1930: The Agent Identity Crisis: Workflow vs. Conversation
One automates invoices silently; the other chats in Slack. Why the industry's favorite word means two totally different things.
#1929: From Vibe Checks to Model Metrics
We stopped "vibe-checking" our AI scripts and built a science fair for models. Here's how we grade them.
#1928: Why Webhook Gateways Beat Direct Wiring
Unscale your chaos: Why Kong beats manual webhook sprawl for auth, routing, and latency.
#1927: Workers vs. Servers: The 2026 Compute Showdown
Is the persistent server dead? We compare Cloudflare Workers, GitHub Actions, and VPS options for modern app architecture.
#1926: How We Built a 2,000-Episode AI Podcast Engine
We pulled back the curtain on the tech stack behind our 1,858th episode. From Gemini to LangGraph, here’s how we automate quality.
#1925: The Plumbing That Keeps Science From Collapsing
Half of all links in academic papers are dead. Here’s the plumbing that keeps knowledge from vanishing.
#1923: Scaling Prosumer Automation to Enterprise
Prosumer tools like n8n break at scale. Here's why durable execution frameworks like Temporal and Prefect are the enterprise upgrade.
#1922: From Plumber to Urban Planner: AI Agent Careers
The job titles are changing from "Zapier Expert" to "Cognitive Architect."
#1919: Android Dev Without Android Studio: Is It Actually Good?
How to ship an Android app without ever opening Android Studio or touching a line of Java.
#1918: When Server Updates Break Your AI Agents
When a third-party MCP server updates its schema, your AI agents can crash. Here's how to build resilient clients that self-heal.
#1917: Herman's Music Hour Vol. 2: Seder Remixes for Passover 5786
Herman presents AI-generated covers of classic Passover Seder songs, produced in Suno — the second installment of Herman's Music Hour.
#1914: Google Invented RAG's Secret Sauce
Before LLMs, Google solved the "hallucination" problem with a two-stage trick that's making a huge comeback.