Tag

software-engineering.

42 writings found

Page 2

Meta's AI Agents Are Now Fixing Their Own Performance Problems

How Meta built a unified AI platform that automates finding and fixing performance issues, recovering hundreds of megawatts without scaling headcount.

How Meta Escaped the Open Source Forking Trap with WebRTC

Meta's multi-year journey to break free from a divergent WebRTC fork reveals hard lessons about managing open source dependencies at scale.

How Meta Escaped the WebRTC Forking Trap Without Breaking Everything

Meta's multi-year migration from a divergent WebRTC fork to upstream reveals hard-earned lessons about maintaining open source dependencies at scale.

When Machines Write Code, Humans Must Learn to Judge

As LLMs generate more code, teams face cognitive surrender and debt proliferation. The future isn't about writing code, it's about verification.

Meta's KernelEvolve: When AI Writes Its Own Performance Code

Meta's KernelEvolve system uses AI agents to automatically optimize low-level hardware kernels, achieving 60% performance gains in hours instead of weeks.

Meta's Adaptive Ranking Model: The Real Cost of Serving Trillion-Parameter Ads

Meta scaled ads recommendations to LLM complexity while keeping latency under a second. Here's why their inference trilemma solution matters beyond advertising.

Treating AI Instructions as Infrastructure, Not Documentation

How encoding team standards as versioned AI instructions solves the consistency problem that plagues AI-assisted development workflows.

Making Team Standards Executable: Infrastructure for AI-Assisted Development

AI coding tools produce wildly different results based on who's prompting. Treating team standards as versioned, executable instructions solves the consistency problem.

Meta's AI is Reshoring American Concrete, One Mix at a Time

How Bayesian optimization is helping U.S. concrete producers ditch imported cement and redesign mixes in days instead of months.

How Facebook Built Friend Bubbles: A Deep Dive into Social ML Architecture

Meta's friend bubbles system combines closeness prediction models, ranking optimization, and performance engineering to surface friend-driven content at scale.

Facebook's Friend Bubbles: When Social Graphs Meet Recommendation Systems

Meta's friend bubbles on Reels reveal how social signals and ML models can coexist in video recommendations without destroying performance.

Facebook's Friend Bubbles: A Masterclass in Social Graph ML

How Meta blends closeness prediction models, multi-task ranking, and prefetch optimization to surface friend-driven content at scale on Reels

Facebook's Friend Bubbles: When Social Graphs Meet Video Recommendations

Meta's approach to blending relationship closeness with content relevance reveals hard truths about building social features at scale.

Patching Security Holes at Scale: When You Have Millions of Lines of Mobile Code

How Meta automates security fixes across massive mobile codebases using AI and custom tooling. A glimpse into enterprise-scale vulnerability management.

Automating Security Fixes at Billions-of-Users Scale

How Meta's security team uses AI to patch vulnerabilities across millions of lines of mobile code without driving engineers insane.

View all writings →