85: Reel Friends: Building Social Discovery that Scales to Billions

How do you add end-to-end encryption to a messenger that people have already been using for years, without taking away the message history they expect to be there? Emma Connor works on the team behind Labyrinth, Messenger's encrypted storage protocol. We get into where the encryption keys actually live, which turns out to be nowhere near Meta, and why a six-digit PIN is far harder to attack than six digits ought to be. Emma also explains the hardware security modules that Meta deliberately locked itself out of, what happens when you lose a device and want it cut out of your account, how key transparency lets you verify who you are talking to without having to trust us, and why Labyrinth 1.1 moved to post-quantum cryptography. All of this and more is discussed in this episode. 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 Opaque Rust Crate - https://crates.io/crates/opaque-ke

Pascal is going on Recharge for August so there will be no regular interview episode. However, we want to hear your questions for our mailbag episode. Send them to us on Instagram (https://www.instagram.com/metatechpod) or Threads (https://www.threads.com/@metatechpod) or via good old email to [email protected].

What changes for you as a developer when the device moves from your pocket to your face? The battery shrinks by an order of magnitude, the thermal budget is whatever won't make your nose uncomfortable, and your mental model of "one process, one device" goes out the window. Rey and Dmitrii talk us through their custom power monitors, how they've extended Perfetto to give a coherent trace across a multi-device system, why robotic arms make surprisingly good QA engineers, and what it takes to catch the kind of regression that quietly costs you thirty minutes of call time. All of this and more is discussed in this episode. 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 Migrating Data Ingestion Systems at Meta Scale: https://engineering.fb.com/2026/05/12/data-infrastructure/migrating-data-ingestion-systems-at-meta-scale/

Your smart glasses run all day on a battery narrower than your pinky finger and building it required reinventing how batteries are made. In this episode, Pascal talks to Karthik and Myuran, the engineers behind Meta's steel can battery technology, to explore why traditional pouch cells couldn't cut it for the ultra-slim temple arms of AI glasses like Meta Ray-Bans and the Oakley Vanguards. Tune in to learn how Meta designed, built, and scaled the batteries powering your glasses, wristbands, and cases from first prototype to mass production. 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 SilverTorch: Index as Model — A New Retrieval Paradigm for Recommendation Systems - https://engineering.fb.com/2026/05/26/ml-applications/silvertorch-index-as-model-new-retrieval-paradigm-recommendation-systems/ Timestamps Intro and News 0:06

Have you ever wondered how Meta makes config rollouts safe at scale? In this episode, Pascal sits down with Ishwari and Joe to discuss Meta's approach for propagating changes across services in seconds and discuss why speed increases the need for strong safeguards. Catch the episode to discover canarying and progressive rollouts, the health checks and monitoring signals used to catch regressions early, and how incident reviews focus on improving systems rather than blaming people. We also hear how data and early AI/ML are slashing alert noise and speeding up bisecting when something goes wrong. 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/.