AI
Artificial intelligence, machine learning, and everything LLM
#4649: Why Open Source Heroes Can't Afford Rent
The code running the internet is maintained by people earning a dollar a year. Why does the market fail to reward our digital commons?
#4648: Graph Engineering: AI Memory Beyond Retrieval
How linked notes and knowledge graphs are turning AI agents from memory tools into discovery engines.
#4642: What Net Neutrality Actually Means for Your Internet
ISPs can see your traffic and shape it. Net neutrality is the only thing stopping them — and right now, the rules are blank.
#4641: Mozilla's Hidden Projects: Beyond the Browser
Mozilla is more than just Firefox. Discover Common Voice, Monitor, Thunderbird, and Rust — the public infrastructure projects shaping the open web.
#4635: Your Phone Is a Firewall Blind Spot — Here's Why
Android ships with no user-facing firewall, and cellular isn't the safe LAN you think. We dig into what's exposed and what actually protects you.
#4631: How Starlink Delivers Real In-Flight Wi-Fi
Why Starlink beats traditional satellite internet on planes — latency, lasers, and phased arrays explained.
#4619: The Token Trap: Why AI Context Windows Confuse Everyone
Token counts are everywhere, but they don't tell you what AI can actually do. Here's what should replace them.
#4610: Why Twilio and RingCentral Never Converge
Twilio and RingCentral both turned telephony into software. So why do they barely compete? The answer is law, not tech.
#4609: The PBX Ledger: What Cloud Phones Really Cost
We traded the PBX for UCaaS and CPaaS. But what did we actually lose — and what did we gain that was impossible before?
#4607: SAP to the Wine Shop: How ERP Tiers Actually Work
Why a wine shop runs on a payment terminal, a mid-market firm runs Priority, and SAP runs the world — without ever being cool.
#4606: Why Resemble Gave Away Its Best Voice Model
Resemble AI sells deepfake detection but open-sourced Chatterbox, a top TTS model. Here's the strategic logic.
#4605: Why Chatterbox Still Leads Open-Source TTS
We break down the architecture of Chatterbox, the open-source TTS model powering this podcast, and why it remains state of the art.
#4604: When Sub-Agents Overwhelm the Orchestrator
Daniel's inventory system hit a wall when parallel sub-agents flooded the orchestrator's context window. We break down the math and the fix.
#4602: The Two Manifests: API vs PNR Explained
Passenger manifests aren't one list — they're two distinct data transmissions with different purposes, formats, and legal frameworks.
#4599: Why Phone Numbers Are Stuck in the 1970s
Why SMS fails on virtual numbers, and what a SIP-first, IPv6-style phone number system would actually take.
#4589: The Answer Reflex: Why AI Models Can't Follow Instructions
DeepSeek passes a simple test that stumps GPT and Claude. Why can't Western models stay in character?
#4588: The Hidden Cost of Conversational AI: Why Stateless LLM Calls Matter
Why conversational AI tools are making batch document processing slower, costlier, and less reliable — and what to do about it.
#4587: Can Agentic AI Finally Break the Google Workspace Grip?
We dig into the real friction points of Google Workspace and whether agentic AI can finally make the monolith obsolete.
#4586: Fixing Stale UI: The 4-Link Chain of Data Flow
Why does a number on screen stay frozen after an upload? We trace the 4-link chain from response to redraw — and where it breaks.
#4585: Why `export` Fails But Files Work: Linux Process Secrets
Why does `wrangler login` work across shells but `export` doesn't? The answer reveals how Linux processes really share data.