From IDEs to AI Agents with Steve Yegge

Key takeaways

AI adoption is critical for engineers, with many still lagging behind in utilizing these tools effectively.
The productivity gains achieved through AI can lead to burnout and necessitate a re-evaluation of work-life balance.
Engagement with new technologies like Gas Town can be both an experimental playground and a source of confusion for developers.
The rapidly changing tech landscape requires developers to adapt quickly and keep up with emerging tools and methodologies.
Predictions for the future suggest that AI will significantly alter coding practices, moving towards a reliance on AI for implementation.

Summary

The Evolution of AI in Software Engineering

Steve Yegge, a software engineer with decades of experience, shares his analysis on how AI is transforming the software engineering landscape. He introduces his concept of the 'eight levels of AI adoption', noting that many engineers remain at the lower levels. The discussion highlights the pitfalls of complacency in the tech industry and the importance of adapting to these changes to remain competitive.

The Dangers and Opportunities of AI for Developers

Yegge describes the 'vampire burnout effect' in the industry where AI can lead to extreme productivity, but at the cost of developer well-being. He draws parallels with past technological shifts, explaining that engineers must find ways to balance productivity with maintaining a healthy work environment. He believes that the core role of AI will be to augment engineers, not replace them.

Gas Town and the Future of Coding

Steve discusses Gas Town, his open-source AI agent orchestrator, sharing insights about its design and functionality. He emphasizes that despite its complexity, many developers should avoid using it without proper understanding of its context. He illustrates the excitement and chaos surrounding the early adoption of such technology and its potential to reshape engineering practices.

Predicting the Future of Software Development

In the concluding sections, Steve shares bold predictions regarding the future of software engineering. He foresees that by the end of 2024, software development will transition into an era where coding by hand is largely supplanted by AI. He urges engineers to prepare for radical changes where personal contributions and human insights become increasingly vital in a world dominated by AI.

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:

• Vibe coding as a software engineer

• The full circle of developer productivity with Steve Yegge

• AI Tooling for Software Engineers in 2026

• The AI Engineering Stack

—

Production and marketing by ⁠⁠⁠⁠⁠⁠⁠⁠https://penname.co/⁠⁠⁠⁠⁠⁠⁠⁠. For inquiries about sponsoring the podcast, email podcast@pragmaticengineer.com.

Get full access to The Pragmatic Engineer at newsletter.pragmaticengineer.com/subscribe