Lenny's Podcast: Product | Career | Growth

chevron_right

“Engineers are becoming sorcerers” | The future of software development with OpenAI’s Sherwin Wu

whatshot 1873 snips

Feb 12, 2026

Guest

Sherwin Wu

Sherwin Wu, Head of Engineering for OpenAI’s API and developer platform, leads work on the API, Agents SDK, and developer tools. He discusses how Codex rewrites software workflows. Short takes on AI cutting review times, engineers managing fleets of agents, widening productivity gaps, and why now is a rare window to leap ahead before roles fully transform.

01:19:39

forum

Ask episode

web_stories

AI Snips

view_agenda

Chapters

menu_book

Books

auto_awesome

Transcript

info_circle

Episode notes

All-Codex Team Experiment

An internal team maintains a 100% Codex-written codebase as an experiment and faces edge-case failures with no escape hatch.
That forced them to encode more tribal knowledge into docs and repo artifacts so agents can perform reliably.

Ecosystem Ripple Effects Of Solo Founders

One-person billion-dollar startups are plausible but imply a boom in many small bespoke support firms and B2B SaaS.
The ecosystem may shift toward many $10–50M companies rather than fewer massive venture outcomes.

Launch An Internal AI Tiger Team

Pair top-down executive buy-in with bottoms-up adoption by forming a dedicated tiger team.
Staff the team with technical-adjacent, enthusiastic users who evangelize, experiment, and share best practices.

Get the Snipd Podcast app to discover more snips from this episode

How much code is written by AI at OpenAI

Codex boosts PR volume and trust

04:17 • 3min

chevron_right

The engineer role shifting to 'sorcery'

07:12 • 5min

chevron_right

Agent reliability and the 100% Codex experiment

12:28 • 3min

chevron_right

Automating and speeding up code reviews

15:27 • 3min

chevron_right

Using multiple models and circular review risks

18:03 • 1min

chevron_right

Clarifying Codex's reach inside OpenAI

19:07 • 29sec

chevron_right

How management changes with AI

19:36 • 5min

chevron_right

One-person billion-dollar startups and second-order effects

24:26 • 7min

chevron_right

Management lessons: empower top performers

31:44 • 6min

chevron_right

Why many AI deployments show negative ROI

38:00 • 4min

chevron_right

Who should staff an AI tiger team

41:57 • 2min

chevron_right

Models will eat your scaffolding

43:59 • 5min

chevron_right

Build for where models are headed

49:06 • 1min

chevron_right

What to expect: longer tasks and better audio

50:34 • 3min

chevron_right

Business process automation opportunity

53:47 • 4min

chevron_right

OpenAI's platform approach and startup advice

57:24 • 5min

chevron_right

ChatGPT apps and ecosystem scale

01:02:12 • 3min

chevron_right

What the API and Agents SDK enable

How to engage and not miss the AI wave

01:09:35 • 2min

chevron_right

Lightning round: books, shows, products, mottos

• Mentioned in 17 episodes

Structure and Interpretation of Computer Programs (SICP)

Julie Sussman

Harold Abelson

Gerald Jay Sussman

This book teaches central ideas of computation by establishing a series of mental models for computation. It covers programming concepts common to all modern high-level programming languages and uses Scheme (or JavaScript in the latest adaptation) to formulate language processors. The book focuses on discovering general patterns for solving specific problems and building software systems that make use of those patterns. It was formerly used as the textbook for MIT's introductory course in computer science and is known as the 'Wizard Book' in hacker culture.

#190

• Mentioned in 117 episodes

Apple in China

The Capture of the World's Greatest Company

Patrick McGee

#2357

• Mentioned in 19 episodes

There Is No Anti-Memetics Division

QNTM

#1204

• Mentioned in 33 episodes

Breakneck, China's Quest to Engineer the Future

Dan Wang

#635

• Mentioned in 51 episodes

The Mythical Man-Month

Essays on Software Engineering

Frederick P. Brooks

In this book, Frederick P. Brooks discusses several key issues in software engineering, most notably 'Brooks's Law,' which states that adding manpower to a late software project makes it later. The book explores the complexities of large programming projects, the difficulties in measuring work in 'man-months,' and the importance of effective communication and team management. It also includes insights from Brooks's experience managing the development of IBM's System/360 and OS/360.

Sherwin Wu leads engineering for OpenAI’s API platform, where roughly 95% of engineers use Codex, often working with fleets of 10 to 20 parallel AI agents.

We discuss:

1. What OpenAI did to cut code review times from 10-15 minutes to 2-3 minutes

2. How AI is changing the role of managers

3. Why the productivity gap between AI power users and everyone else is widening

4. Why “models will eat your scaffolding for breakfast”

5. Why the next 12 to 24 months are a rare window where engineers can leap ahead before the role fully transforms

—

Brought to you by:

DX—The developer intelligence platform designed by leading researchers

Sentry—Code breaks, fix it faster

Datadog—Now home to Eppo, the leading experimentation and feature flagging platform

—

Episode transcript: https://www.lennysnewsletter.com/p/engineers-are-becoming-sorcerers

—

Archive of all Lenny's Podcast transcripts: https://www.dropbox.com/scl/fo/yxi4s2w998p1gvtpu4193/AMdNPR8AOw0lMklwtnC0TrQ?rlkey=j06x0nipoti519e0xgm23zsn9&st=ahz0fj11&dl=0

—

Where to find Sherwin Wu:

• X: https://x.com/sherwinwu

• LinkedIn: https://www.linkedin.com/in/sherwinwu1

—

Where to find Lenny:

• Newsletter: https://www.lennysnewsletter.com

• X: https://twitter.com/lennysan

• LinkedIn: https://www.linkedin.com/in/lennyrachitsky/

—

In this episode, we cover:

(00:00) Introduction to Sherwin Wu

(03:10) AI’s role in coding at OpenAI

(06:53) The future of software engineering with AI

(12:26) The stress of managing agents

(15:07) Codex and code review automation

(19:29) The changing role of engineering managers

(24:14) The one-person billion-dollar startup

(31:40) Management lessons

(37:28) Challenges and best practices in AI deployment

(43:56) Hot takes on AI and customer feedback

(48:57) Building for future AI capabilities

(50:16) Where models are headed in the next 18 months

(53:35) Business process automation

(57:22) OpenAI’s ecosystem and platform strategy

(01:00:50) OpenAI’s mission and global impact

(01:05:21) Building on OpenAI’s API and tools

(01:08:16) Lightning round and final thoughts

—

Referenced:

• Codex: https://openai.com/codex

• OpenAI’s CPO on how AI changes must-have skills, moats, coding, startup playbooks, more | Kevin Weil (CPO at OpenAI, ex-Instagram, Twitter): https://www.lennysnewsletter.com/p/kevin-weil-open-ai

• OpenClaw: https://openclaw.ai

• The creator of Clawd: “I ship code I don’t read”: https://newsletter.pragmaticengineer.com/p/the-creator-of-clawd-i-ship-code

• The Sorcerer’s Apprentice: https://en.wikipedia.org/wiki/The_Sorcerer%27s_Apprentice_(Dukas)

• Quora: https://www.quora.com

• Marc Andreessen: The real AI boom hasn’t even started yet: https://www.lennysnewsletter.com/p/marc-andreessen-the-real-ai-boom

• Sarah Friar on LinkedIn: https://www.linkedin.com/in/sarah-friar

• Sam Altman on X: https://x.com/sama

• Nicolas Bustamante’s “LLMs Eat Scaffolding for Breakfast” post on X: https://x.com/nicbstme/status/2015795605524901957

• The Bitter Lesson: http://www.incompleteideas.net/IncIdeas/BitterLesson.html

• Overton window: https://en.wikipedia.org/wiki/Overton_window

• Developers can now submit apps to ChatGPT: https://openai.com/index/developers-can-now-submit-apps-to-chatgpt

• Responses: https://platform.openai.com/docs/api-reference/responses

• Agents SDK: https://platform.openai.com/docs/guides/agents-sdk

• AgentKit: https://openai.com/index/introducing-agentkit

• Ubiquiti: https://ui.com

• Jujutsu Kaisen on Crunchyroll: https://www.crunchyroll.com/series/GRDV0019R/jujutsu-kaisen?srsltid=AfmBOoqvfzKQ6SZOgzyJwNQ43eceaJTQA2nUxTQfjA1Ko4OxlpUoBNRB

• eero: https://eero.com

• Opendoor: https://www.opendoor.com

—

Recommended books:

• Structure and Interpretation of Computer Programs: https://www.amazon.com/Structure-Interpretation-Computer-Programs-Engineering/dp/0262510871

• The Mythical Man-Month: Essays on Software Engineering: https://www.amazon.com/Mythical-Man-Month-Software-Engineering-Anniversary/dp/0201835959

• There Is No Antimemetics Division: A Novel: https://www.amazon.com/There-No-Antimemetics-Division-Novel/dp/0593983750

• Breakneck: China’s Quest to Engineer the Future: https://www.amazon.com/Breakneck-Chinas-Quest-Engineer-Future/dp/1324106034

• Apple in China: The Capture of the World’s Greatest Company: https://www.amazon.com/Apple-China-Capture-Greatest-Company/dp/1668053373

—

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

—

Lenny may be an investor in the companies discussed.

To hear more, visit www.lennysnewsletter.com

Home Top podcasts Popular guests Top books