scripod.com
Inside Devin: The world’s first autonomous AI engineer that's set to write 50% of its company’s code by end of year | Scott Wu (CEO and co-founder of Cognition)

Overview

Shownote

Highlights

Transcript

Chapters

Pins

Inside Devin: The world’s first autonomous AI engineer that's set to write 50% of its company’s code by end of year | Scott Wu (CEO and co-founder of Cognition)

Lenny's Podcast: Product | Career | Growth

2025/05/04
Lenny's Podcast: Product | Career | Growth

Lenny's Podcast: Product | Career | Growth

2025/05/04
OverviewShownoteHighlightsTranscriptChaptersPins

Shownote

Scott Wu is the co-founder and CEO of Cognition, the company behind Devin—the world’s first autonomous AI software engineer. Unlike other AI coding tools, Devin works like an autonomous engineer that you can interact with through Slack, Linear, and GitHub,...

Highlights

Scott Wu, co-founder and CEO of Cognition, discusses Devin, the world's first autonomous AI software engineer. Unlike traditional AI coding tools, Devin operates autonomously through platforms like Slack, Linear, and GitHub, mimicking interactions with a remote engineer. This podcast explores how Devin has evolved from handling basic tasks to contributing significantly to Cognition’s codebase, reshaping the future of software engineering.
07:28
Devin outperforms humans in some areas while lagging in others, showcasing its evolving capabilities.
09:14
Devin enhances team productivity by acting as a junior buddy and accumulating knowledge.
12:46
Many top AI companies pivot significantly before finding success.
19:51
Devin merges hundreds of pull-requests into the codebase monthly.
22:20
Building Devin aims to let engineers shift from 'bricklayers' to 'architects'.
25:18
Learning to code helps develop logical problem-solving and understanding of computer models and abstractions.
32:53
Capabilities improvement will lead to a shift in software-building processes.
34:38
Devin can work synchronously or asynchronously and makes pull requests.
42:20
Devin can understand large code bases by first focusing on high-level architecture and then zooming in on details.
44:50
Adding a Devin label to tasks enables automated analysis and insights.
49:01
A key debate was whether Devin should be a single project experience or a suite of tools.
55:17
Users can interact with products without looking at code.
59:40
Devin can make pull requests and work based on reviews.
1:01:57
Base intelligence is nearly sufficient; focus shifts to real-world idiosyncrasies.
1:04:14
AI grows exponentially without hardware distribution constraints.
1:10:10
Working with Devin requires new paradigms, akin to the shift when Python was invented.
1:20:09
Reimagine things from the ground up considering where technology is headed.
1:22:33
AI allows people to multiply their capabilities.

Chapters

Introduction to Scott Wu and Devin
00:00
Scaling and future prospects
09:13
Devin's origin story
10:23
The idea of Devin as a person
17:26
How a team of “Devins” are already producing 25% of Cognition’s pull requests
22:19
Important skills in the AI era
25:17
How Cognition’s engineering team works with Devin's
30:21
Live demo
34:37
Devin’s codebase integration
42:20
Automation with Linear
44:50
What Devin does best
46:53
The future of AI in software engineering
52:56
Moats and stickiness in AI
57:13
The tech that enables Devin
1:01:57
AI will be the biggest technology shift of our lives
1:04:14
Adopting Devin in your company
1:07:25
Startup wisdom and hiring practices
1:15:13
Lightning round and final thoughts
1:22:32

Transcript

Scott Wu: Our whole team is only like 15 engineers. We use a ton of Devin when we're building Devin. Most folks on the team are definitely working with up to five Devons at once. And so Devin merges, like several hundred pull requests into production in th...