AI Summary
5 min readSteve Yegge, a 40-year veteran of Amazon and Google, recently built an open-source AI agent orchestrator called Gas Town and co-authored the book Vibe Coding. In this conversation, he argues that the software engineering profession is undergoing a shift as profound as the move from assembly language to high-level languages—except it is happening in months, not decades. He predicts that small teams of 2 to 20 people will soon rival the output of big tech companies, and that 70% of engineers are still stuck at the lowest levels of AI adoption, using tools like Copilot while a "barbarian horde" of engineers using Opus 4.5 is about to disrupt them.
The 8 Levels of AI Adoption
Yegge has mapped out a spectrum of how engineers use AI, from level one (no AI) to level eight (running multiple agents in parallel). At level two, engineers ask yes-or-no questions inside their IDE. At level three, they start trusting the AI enough to say "just do your thing." By level four, they are squeezing the code out, focusing on the conversation with the agent rather than reviewing diffs. At level five, they stop coding in the IDE entirely and just talk to the agent. Level six is where things get interesting: the agent is busy, so you fire up another one, and then another, and you become addicted to multiplexing between them. Level seven is the mess that results from accidentally texting the wr
Continue reading the full summary in the app — free to try.
Read Full Summary →Free • No credit card required
Never miss an episode of The Pragmatic Engineer
Get every new episode summarized in your inbox — free, ~5 minutes to read.
No spam. Unsubscribe anytime.
What you'll learn
- 1 (02:06) **Early blog post impact** - Steve recounts how "Execution in the Kingdom of Nouns" and "Rich Programmer Food" shaped careers and industry views on compilers and language design
- 2 (05:18) **What engineers need to know keeps shifting** - Foundational skills like assembly and bit manipulation have moved up the abstraction ladder over 40 years
- 3 (10:34) **First reaction to LLMs** - Skeptical until ChatGPT-3.5 produced coherent Emacs Lisp; curve-watching began immediately
- 4 (13:06) **"Days of coding by hand are over"** - Realization came over a year earlier after conversations with language inventors like Dr. Eric Meyer
- 5 (17:48) **Big-tech headcount reduction dynamic** - Companies are turning a "productivity dial" that effectively removes ~50% of engineers to fund AI usage for the rest
- 6 (21:50) **8 levels of AI adoption** - Practical spectrum from "no AI" to running multiple coordinated agents in parallel
- 7 (24:14) **Death of the IDE debate** - IDEs are viewed as temporary tool aggregators that will be replaced by conversational agent interfaces
+ Full timestamped outline available in the app
Show Notes
Brought to You By:
• Statsig — The unified platform for flags, analytics, experiments, and more.
• Sonar – The makers of SonarQube, the industry standard for automated code review
• WorkOS – Everything you need to make your app enterprise ready.
—
Steve Yegge has spent decades writing software and thinking about how the craft evolves. From his early years at Amazon and Google, to his influential blog posts, he has often been early at spotting shifts in how software gets built.
In this episode of Pragmatic Engineer, I talk with Steve about how AI is changing engineering work, why he believes coding by hand may gradually disappear, and what developers should focus on, instead. We discuss his latest book, Vibe Coding, and the open-source AI agent orchestrator he built called Gas Town, which he said most devs should avoid using.
Steve shares his framework for levels of AI adoption by engineers, ranging from avoiding AI tools entirely, to running multiple agents in parallel. We discuss why he believes the knowledge that engineers need to know keeps changing, and why understanding how systems evolve may matter more than mastering any particular tool.
We also explore broader implications. Steve argues that AI’s role is not primarily to replace engineers, but to amplify them. At the same time, he warns that the pace of change will create new kinds of technical debt, new productivity pressures, and fresh challenges for how teams operate.
—
Timestamps
(00:00) Intro
(01:43) Steve’s latest projects
(02:27) Important blog posts
(04:48) Shifts in what engineers need to know
(10:46) Steve’s current AI stance
(13:23) Steve’s book Vibe Coding
(18:25) Layoffs and disruption in tech
(31:13) Gas Town
(40:10) New ways of working
(51:08) The problem of too many people
(54:45) Why AI results lag in business
(59:57) Gamification and product stickiness
(1:04:54) The ‘Bitter Lesson’ explained
(1:07:14) The future of software development
(1:23:06) Where languages stand
(1:24:47) Adapting to change
(1:27:32) Steve’s predictions
—
The Pragmatic Engineer deepdives relevant for this episode:
< More from this podcast
The Pragmatic Engineer →