Subvolts take AI codemods secure millions of lines of Android code at Meta. Feb 27, 2026 - Developers
- Learn how AI can automate security updates across millions of lines of code for Android apps.
- Business
- Understand the engineering challenges and AI solutions for maintaining security at massive scale.
This episode provides a solid interview on a practical AI application for secure mobile development at a major tech company.
83: Patch Me If You Can: AI Codemods for Secure-by-Default Android Apps
Audio streams from Meta. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Meta Tech Podcast episode 83 features Alex and Tanu discussing the challenges of making Meta's mobile frameworks more secure at scale. Host Pascal Harris explores how AI codemods help achieve secure-by-default Android apps, addressing monumental engineering tasks involving millions of lines of code and thousands of engineers. The conversation highlights the intersection of security, automation, and AI in mobile development.
Imagine updating a giant software project to be safer. This episode explains how Meta uses smart computer programs, powered by AI, to automatically fix millions of lines of code. This makes Android apps more secure for everyone without slowing down the engineers.
This episode offers insights into large-scale software security and the practical application of AI in mobile development. It is for engineers and product managers working on complex mobile applications or interested in AI-driven code transformation. The discussion aligns with current frontier lab efforts in using AI for code generation and security, particularly Meta's ongoing work in this area.
- HostPascal Harris
- GuestAlex
- GuestTanu
- Episode Title: 83: Patch Me If You Can: AI Codemods for Secure-by-Default Android Apps
- Show: Meta Tech Podcast
- Length: 48 minutes
- Topic: Making Meta's mobile frameworks more secure at scale using AI codemods.
At Meta, even seemingly simple engineering tasks—like updating an API—become monumental undertakings when you're dealing with millions of lines of code and thousands of engineers, especially if the changes are security-related. In today's episode, Pascal talks to Alex and Tanu about the challenges and learnings from the journey of making Meta's mobile frameworks more secure at a scale few companies ever experience. Tune in to this episode and join us as we explore the compelling crossroads of security, automation, and AI within mobile development.
Got feedback? Send it to us on Threads (https://threads.net/@metatechpod), Instagram (https://instagram.com/metatechpod) and don't forget to follow our host Pascal (https://mastodon.social/@passy, https://threads.net/@passy_). Fancy working with us? Check out https://www.metacareers.com/.
Links
-
How AI Is Transforming the Adoption of Secure-by-Default Mobile Frameworks - https://engineering.fb.com/2025/12/15/android/how-ai-transforming-secure-by-default-mobile-frameworks-adoption/
-
RCCLX: Innovating GPU Communications on AMD Platforms - https://engineering.fb.com/2026/02/24/data-center-engineering/rrcclx-innovating-gpu-communications-amd-platforms-meta/
-
The Death of Traditional Testing: Agentic Development Broke a 50-Year-Old Field, JiTTesting Can Revive It - https://engineering.fb.com/2026/02/11/developer-tools/the-death-of-traditional-testing-agentic-development-jit-testing-revival/
Timestamps
-
Intro & News 0:06
-
Meet the Product Security Team 2:07
-
Understanding the Intent System 4:13
-
Security Challenges in Android's Intent System 6:44
-
Proposed Solutions for Intent Security 9:39
-
Meta's Unique Challenges at Scale 12:34
-
Implementing a Secure Link Launcher Framework 15:32
-
Leveraging AI for Contextual Understanding 17:55
-
Navigating AI-Driven Code Modifications 20:47
-
Developer Experience with AI Code Mods 21:49
-
Validation Challenges in AI Code Generation 25:37
-
Evolution of AI in Code Modifications 29:29
-
Identifying AI's Strengths in Security 36:20
-
Future Directions in AI and Framework Development 42:58
-
Outro 46:58
- AI Codemods
- Alex and Tanu
- Smart computer programs that use AI to automatically change code for security improvements.
- Secure-by-Default
- Alex and Tanu
- Software designed to be safe and secure right from the start, without needing extra configuration.
38 min41 min87: Everything is Power: Battery Life Engineering for AI Glasses
WithRey, Dmitrii
43 min86: A Hard Cell: Engineering Ultra-Narrow Batteries for AI Glasses
WithKarthik, Myuran
39 min85: Reel Friends: Building Social Discovery that Scales to Billions
WithJoseph, Subasree
Same guests, other shows
35 min50: De-identified authentication at scale
WithAlex, Haozhi
48 min
1 h 05Questions people ask
- What are AI codemods?
- AI codemods are automated tools that use artificial intelligence to modify code, in this case, to improve the security of Android applications.
- Why is updating code at Meta a big challenge?
- Meta deals with millions of lines of code and thousands of engineers, making even simple updates, especially for security, a monumental undertaking.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Meta.