How Meta reduced diff authoring time by 40%

<p>Meta researcher Moritz Beller joins Brian Houck to discuss how Meta measures developer productivity. Moritz explains diff authoring time and how Meta uses it to evaluate tools and guide engineering decisions. They explore how AI is changing engineers’ work and revealing gaps in traditional metrics. They also revisit Moritz’s “Mind the Gap” study and discuss the promise and risks of AI agents for testing.</p><p><br></p><p><strong>Where to find Moritz Beller:</strong></p><p>• LinkedIn: <a href="https://www.linkedin.com/in/inventitech" target="_blank" rel="ugc noopener noreferrer">https://www.linkedin.com/in/inventitech</a> </p><p>• X: <a href="https://x.com/Inventitech" target="_blank" rel="ugc noopener noreferrer">https://x.com/Inventitech</a> </p><p>• GitHub: <a href="https://github.com/Inventitech" target="_blank" rel="ugc noopener noreferrer">https://github.com/Inventitech</a> </p><p>• Website: <a href="https://inventitech.com" target="_blank" rel="ugc noopener noreferrer">https://inventitech.com</a> </p><p><br></p><p><strong>Where to find Brian Houck: </strong></p><p>• LinkedIn: <a href="https://www.linkedin.com/in/brianhouck" target="_blank" rel="ugc noopener noreferrer">⁠⁠⁠https://www.linkedin.com/in/brianhouck⁠⁠⁠</a></p><p><br></p><p><strong>In this episode, we cover:</strong></p><p>(00:00) Intro</p><p>(02:10) Moritz’s role at Meta</p><p>(04:01) Measuring diff authoring time</p><p>(08:20) Measuring A/B experiments</p><p>(12:11) What diff authoring time reveals</p><p>(14:45) Planning and leadership reporting</p><p>(18:36) Why Meta measures teams, not individuals</p><p>(22:33) Where developer time goes with AI</p><p>(26:06) AI’s impact on junior and senior developers</p><p>(27:18) Capturing invisible work with AI</p><p>(29:32) The “Mind the Gap” study</p><p>(33:40) Revisiting “Mind the Gap” in 2026</p><p>(38:32) AI agents for software testing</p><p>(41:49) What remains hard to measure</p><p><br></p><p><strong>Referenced:</strong></p><p>• <a href="https://getdx.com/report/State-of-AI-Impact-in-Engineering-Q2-Report" target="_blank" rel="ugc noopener noreferrer">State of AI Impact in Engineering Q2 Report 2026</a></p><p>• <a href="https://arxiv.org/abs/2606.00438" target="_blank" rel="ugc noopener noreferrer">GitHub Copilot and Developer Productivity: An Observational Dose-Response Analysis</a></p><p>• <a href="https://qb4.acm.org/detail.cfm?id=3807966" target="_blank" rel="ugc noopener noreferrer">From Technical Debt to Cognitive and Intent Debt</a>