Hi, I'm Scott Galloway.

Cooking with DiSE (Part 3): Untrustworthy Gods - When Your LLM Might Be Lying to You

In which we discover that your friendly AI assistant might have ulterior motives (and what to do about it) Note: This is Part 3 in the "Cooking with DiSE" series. If you haven't read Parts 1-2, you might want to—though this one stands alone as a slightly…

Towards 1.0: Making Umami.NET Production Ready

When I first integrated Umami analytics into my blog platform, I quickly ran into a frustrating reality: Umami's API documentation is... let's be charitable and call it "minimal." Error messages are cryptic at best, non-existent at worst. Parameters change…

AI as Disciplined Software: “I Think I Should Leave”

Evolving AI Workflows and the Drive to Simplicity Fancy paying me to turn this into a proper product? Drop me a line: scott.galloway+[email protected] The Thought That Started Everything Why does a human brain run real-time cognition on 20 watts—while our best AI…

How I Build Software: Make It Work, Make It Pretty, Lock It Down

Why I write tests last, and why that's not what you think it means Controversial take: Test-Driven Development is a brilliant practice that solves the wrong problem for most creative work. Here's what works better. The Three Phases of Building Software (That…

Semantic Intelligence: Part 10 - The DiSE Cooker: When Tools Cook Themselves Into Workflows

The finale of the Semantic Memory series. The beginning of something stranger. Note: This is Part 10—the last in the Semantic Memory series and the first in the DiSE Cooker series. We're moving from theory to practice, from "how tools work" to "what happens…

Semantic Intelligence: Part 9 - Self-Healing Tools Through Lineage-Aware Pruning

When your tools break themselves, your system should remember why and never repeat the mistake When *DiSE commits murder. <img src="https://github.com/scottgal/mostlylucid.dse/raw/main/logo.png?height=200" alt="mostlylucid-dse logo" height="200px"…

Cooking with DiSE (Part 2): Graduated Apprenticeships - Training Workflows to Run Without a Safety Net

When your workflows learn to walk without training wheels (and you stop paying for babysitters) Note: This is Part 2 in the "Cooking with DiSE" series, exploring practical patterns for production-scale workflow evolution. Today we're talking about something…

Semantic Intelligence: Part 8 - Tools All The Way Down: The Self-Optimizing Toolkit

When your tools track themselves, evolve themselves, and choose themselves Note: This is Part 8 in the Semantic Intelligence series. Part 7 covered the overall DSE architecture. This article dives deep into something I glossed over: how the tools themselves…

Semantic Intelligence: Part 7 - The Real Thing! Experimenting with Directed Synthetic Evolution

When theory meets reality and code starts evolving itself Note: Inspired by thinking about extensions to mostlylucid.mockllmapi and material for the (never to be released but I like to think about it 😜) sci-fi novel "Michael" about emergent AI Note: This is…

Semantic Intelligence: Part 6 - Directed Synthetic Evolution and Global Consensus

When optimization systems develop diplomacy Note: Inspired by thinking about extensions to mostlylucid.mockllmapi and material for the (never to be released but I like to think about it 😜) sci-fi novel "Michael" about emergent AI Beyond Guilds: What Comes…