Loading…
Latest reads
The engineering internet, summarised so you can actually read it.
Amazon ·
Diverse reasoning traces teach LLMs to make better decisions
Large language models typically rely on supervised fine-tuning with a single human-verified reasoning trace per example, which limits reasoning breadth and causes mode collapse when attempting parallel reasoning. Researchers presented set-supervised fine tuning (SSFT) and global forking policy optimization (GFPO) to teach models diverse problem-solving strategies. SSFT represents reasoning as a set of complete solution paths paired with global forking tokens, utilizing bipartite matching to achieve order-invariant training and specialized tokens. GFPO applies lightweight reinforcement learning to select the optimal forking token upfront, detaching gradients from generated rollouts to ensure stable optimization. On standard reasoning and coding benchmarks, the combined framework increased single-shot accuracy by 5% to 7% while improving pass@k diversity without degrading pass@1 accuracy.
Sheng Jia, Xiao Wang, Shiva KasiviswanathanAI as the Next Abstraction Layer: How I see engineering evolving at Thumbtack
Thumbtack is transitioning its engineering workflow from ad-hoc tool experimentation to end-to-end agentic software development. Unlike previous deterministic abstractions such as compilers or high-level languages, artificial intelligence introduces non-determinism where identical prompts can produce varying code and trade-offs. Because consumer marketplace experiments still require weeks for behavioral signals to stabilize, accelerated implementation primarily helps teams prepare cleaner experiment designs and parallelize hypotheses within experimentation bandwidth constraints. Consequently, day-to-day engineering responsibilities shift upstream from manual coding toward problem framing, system architecture, validation, and co-designing features with product managers. Teams maintain technical sharpness by rigorously reviewing generated code while accepting that long-term specialization above the abstraction layer will become standard across the organization.
Ananda Kanagaraj SankarGrab ·
The Hugo evolution: Engineering Grab's unified, one-click data ingestion platform with Apache Flink
Grab's self-service data platform, Hugo, faced significant onboarding friction as streaming pipelines expanded across fragmented systems like Kafka Connect, custom Go applications, and Spark. Engineering teams struggled with cross-platform configuration translations and brittle, manual schema mappings that stretched onboarding over several days. To resolve these bottlenecks, Grab modernized the ingestion architecture by introducing a centralized automation layer powered by Apache Flink and Flink CDC. The updated platform dynamically retrieves Protobuf schemas from Confluent Schema Registry and ingests MySQL binlogs directly into queryable Hive tables without intermediate Kafka hops. This shift dropped pipeline onboarding times to roughly six minutes for Kafka and three minutes for MySQL CDC, driving more pipeline adoptions in one year than in the previous five.
Shuguang XiangMaking User-Sequence Data More Cost-Efficient, Faster, and Easier to Use
User sequences serve as core primitives powering machine learning models across ranking, retrieval, and recommendation surfaces at Pinterest. Managing these sequences previously caused high infrastructure costs, operational fragility, and data drift between offline training pipelines and online serving systems. In response, engineering teams redesigned the platform around a single definition executed across multiple runtimes, including real-time streaming, batch backfills, and online inference. The updated architecture pairs a unified enrichment engine with columnar time-partitioned storage and standardized validation tiers. Consequently, the redesign achieved lower storage and network costs, faster signal onboarding via configuration, and improved engagement metrics across major recommendation surfaces.
Pinterest EngineeringDropbox ·
Introducing Nova, our internal platform for coding agents
Dropbox developed Nova, an internal platform that runs AI coding agents in isolated cloud environments integrated with their Bazel monorepo. The platform supports both interactive developer workflows and autonomous background tasks, such as automated CI debugging, flaky test remediation, and codebase-wide migrations. By pairing code generation with automated validation and strict execution guardrails, Nova ensures generated fixes are tested and reproducible.
Ilya Yakovlev,Andrew Cheung,Binoy Dash,Simran Jumani,Dmitriy Meyerzon,Mark Breitenbach,Ishan Mishra,Kazuaki Okumura,Mike White,Kevin AltschulerSentry ·
The product analytics you already have
Software engineers frequently rely on separate product analytics tools and teams to answer user behavior questions, creating disjointed data models and delayed insights. Existing debugging telemetry within tools like Sentry—specifically spans, structured logs, and application metrics—can serve as the primary source for product metrics. Developers enrich request spans with business-level attributes, record discrete business events through wide structured logs, and track KPIs with metric counters and distributions. This unified telemetry links business outcomes directly to underlying traces, errors, releases, and source code lines, enabling immediate root-cause analysis and automated alerts. While multi-session cohort and funnel aggregation remains a current tooling gap, standard telemetry solves day-to-day adoption, performance, and revenue questions.
Rahul ChhabriaYelp ·
How Partition Access Visualizations Reduced our Data Lake S3 Cost by 33%
Data teams at Yelp struggled to identify table consumers and track how datasets were accessed across their petabyte-scale data lake. To solve this, the team built a usage attribution system using Amazon S3 server access logs to visualize time-based partition keys against access timestamps and IAM roles. These visualizations revealed distinctive patterns for daily batch jobs, backfills, and ad hoc queries, guiding migrations of thousands of tables to Apache Iceberg format. Furthermore, Yelp implemented a Default Access Retention strategy gated by IAM bucket policies to prevent accidental queries from resetting S3 Intelligent Tiering transitions. Combining these granular usage insights with targeted S3 storage classes reduced Yelp's S3 storage costs by 33 percent.
Nick Del Nano, Data StreamingYelp ·
Optimizing Our Build Times by Migrating from Webpack to Rspack
As Yelp's JavaScript monorepo expanded over time, Webpack build speeds became a significant engineering bottleneck. To resolve this without rewriting complex configurations, the team selected Rspack for its direct compatibility with existing Webpack setups and plugins. Yelp implemented an adapter pattern to generate Rspack configurations dynamically from original Webpack files, enabling a staged opt-in rollout across development tools and CI environments. Following the initial migration, engineers addressed performance issues in barrel files using automated codemods to replace star re-exports and import-then-export patterns with named re-exports. Combined with Rspack's portable persistent caching, the migration reduced integration build times by approximately 52 percent and warm cache builds by up to 80 percent.
Benson Pan, Software EngineerAirbnb ·
Scaling Airbnb’s identity graph with a unified knowledge graph infrastructure
Airbnb migrated its massive identity graph from a third-party graph database vendor to a unified, in-house knowledge graph platform to solve long-tail latency and scaling bottlenecks. Built on JanusGraph with AWS DynamoDB for persistence and OpenSearch for indexing, the new architecture decouples storage operations from graph traversal logic. The migration improved P99 query latency, eliminated routine instance reboots, and supported a tenfold increase in write throughput.
Lucen ZhaoDocker ·
Coding Agent Horror Stories: The Security Crisis Threatening Developer Infrastructure
Autonomous AI coding agents increasingly handle developer workflows, but their execution model introduces critical security risks. Operating with the executing user's full permissions, these agents can read ambient secrets, inherit cloud credentials, and run destructive shell commands without human intervention. Documented incidents between October 2024 and February 2026 reveal systemic hazards, including unintentional home directory deletions and increased security vulnerabilities in generated code. To address these vulnerabilities, Docker Sandboxes isolate agent execution within dedicated microVMs, preventing access to the host filesystem and blocking common credential paths by default. Routing changes through Git worktrees and restricting network egress ensures that agent actions remain strictly bounded and reviewable before affecting main branches or production infrastructure.
Jennifer KohlAmazon ·
Making LLMs faster without sacrificing accuracy
Standard scaling laws optimize parameter count and training data budgets to minimize loss but ignore internal Transformer architecture configurations. To address throughput disparities among equally sized models, researchers developed a scaling framework incorporating hidden size, the multilayer perceptron to attention parameter ratio, and grouped-query attention. The method calibrates a correction surface over standard Chinchilla scaling laws to independently optimize separable architectural parameters for target accuracy. Evaluated across more than 200 models up to three billion parameters, the framework produced the Panda model family for maximum accuracy and the Surefire family for Pareto efficiency. Surefire models matched or exceeded LLaMA-3.2 accuracy while increasing inference throughput by 12% to 47% across vLLM and SGLang serving systems on modern GPUs.
Tao Yu, Youngsuk ParkGrab ·
Scaling developer experience: How we improved Android Studio in a large monorepo
Grab's passenger Android monorepo contains roughly 2,000 modules and 11 million lines of code, leading to IDE sync times exceeding 35 minutes on cold starts. While Bazel handles application builds, Android Studio relies on Gradle sync to construct its project model, requiring Gradle to evaluate every module during configuration. To solve this bottleneck, the team built a custom Focus plugin that restricts IDE syncing to target modules and their direct dependencies. The architecture reuses a static dependency graph generated during existing Gradle-to-Bazel migration tasks to eliminate the Gradle configuration phase during module selection. An IntelliJ extension and a Groovy method-shadowing technique in settings.gradle allow developers to configure focused modules directly through a graphical user interface.
Rifqi FahmiGithub ·
From latency to instant: Modernizing GitHub Issues navigation performance
GitHub Issues addressed navigation latency by shifting workloads to the client using a local-first, stale-while-revalidate architecture. To evaluate perceived delays, the team tracked user transitions through Highest Priority Content thresholds, aiming for instant rendering in under 200 milliseconds. The core implementation added a persistent client-side cache using IndexedDB, paired with a synchronous in-memory tier to serve hot issue payloads without asynchronous overhead. A selective preheating mechanism resolves missing cache entries for high-intent links without overburdening backend capacity with redundant requests. Following broad rollout, the proportion of instant React soft navigations increased from 4% to approximately 22%, yielding an overall cache-hit ratio of around 33%.
Natalie GuevaraAmazon ·
Promptimus: Improving already good LLM prompts with zero manual engineering
Enterprise applications rely on mature large language model prompts that incorporate intricate business logic and regulatory constraints, making further optimization and cross-model migration challenging. Promptimus automates prompt refinement through a four-step iterative loop that evaluates candidate prompts against decomposed metric checkpoints, diagnoses failure bottlenecks, and generates targeted improvement strategies. The system operates either via full prompt rewrites in standard mode or through surgical, programmatic find-and-replace edits in edit mode to preserve structured taxonomies and schemas. Tested across multimodal classification and code generation tasks, the framework achieves performance gains with small development datasets of 20 to 50 samples. Amazon is making the model-agnostic optimization system available through Amazon Bedrock to support enterprise generative-AI model migration without manual engineering.
Zhengyuan Shen, Yunfei Bai, Sullam Jeoung, Shuai WangSentry ·
New ways to agentically build and edit dashboards
Pre-configured monitoring templates often fail to meet organization-specific needs, forcing developers to manually build dashboards widget by widget. Sentry introduced AI-agent-powered dashboard creation and editing in open beta, alongside CLI management tooling and template revisions. Users can prompt an AI chat interface to build or adjust dashboards, duplicate and customize uneditable Sentry-built templates, or execute dashboard commands directly in their terminal. Dashboards leverage issue, tracing, and application metric data across frontend, backend, mobile, and framework-specific views like Next.js and Laravel. Edits made through the UI, CLI, or AI agent are automatically tracked in a revision history that supports one-click rollbacks.
Ben Coe, Steve ZegaliaAn Engineer’s Guide to Better AI Skills: Implementing a Testing Process to Optimize Agent…
Software engineers deploying AI agents often encounter unreliable skill invocation for repository-specific architectures, such as Pinterest's iOS framework. To quantify and resolve this issue, a Bash test harness piped positive and negative prompts into Pin-agent and Claude Code while parsing streamed JSON logs for execution signatures. Initial vanilla benchmarks yielded baseline accuracies of 73% for GPT 5.2-codex and 62% for Opus 4.5 Claude. Optimizations such as expanding YAML frontmatter descriptions with architectural context, utilizing capitalized imperative directives, and adding reference tables in AGENTS.md raised invocation rates. Both agents reliably loaded skills when prompts contained explicit invocations, demonstrating that empirical testing paired with descriptive prompting stabilizes agent skill adoption.
Pinterest EngineeringMongoDB ·
Fighting Tool Sprawl: The Case for AI Tool Registries
Rapid enterprise AI agent adoption without centralized infrastructure introduces widespread tool sprawl, duplicated engineering effort, and severe operational opacity. Individual application teams frequently build ad hoc, undocumented integrations, leaving security teams unable to discover, audit, or approve active agent capabilities. Internal enterprise tool registries address this coordination failure by establishing an organization-specific catalog tailored to internal security policies, data, and compliance requirements. A production-grade registry delivers core discovery and version tracking functionality while surfacing security certification metadata and enabling consistent identity-scoped access control across teams. Organizations establishing centralized tool infrastructure can accelerate agent onboarding, implement deny-by-default governance policies, and mitigate technical debt before uncoordinated deployments compound across the enterprise.
Peter RichardsSentry ·
From vibe code to production-ready: observability for Next.js and Supabase apps
AI-assisted software development often generates functional code that lacks proper instrumentation, leading to unindexed database queries, N+1 patterns, and fragmented connection strategies. While Supabase provides built-in query analytics, security advisors, and subsystem logs, it cannot trace distributed requests across the entire application stack. Integrating Sentry bridges this visibility gap by establishing distributed traces across Next.js frontends, Deno-based Supabase Edge Functions, and Postgres databases. Teams can forward Supabase logs into dedicated Sentry projects and configure runtime integrations to automatically detect performance bottlenecks such as slow spans and Web Vitals regressions. Furthermore, integrating Model Context Protocol servers allows Sentry's Seer debugger to identify root causes and generate automated fixes for emerging issues.
Sergiy DybskiyEnhancing Ad Relevance: Integrating Real-Time Context into Sequential Recommender Models
Pinterest's sequential ads candidate generator inferred user embeddings offline from historical offsite conversions, which lacked real-time browsing context. Consequently, less than 1% of impressions on the Related Pins surface were attributed to this generator because its retrieved candidates struggled in downstream ranking. To resolve this limitation, engineers developed the Contextual Sequential Two Tower Model, integrating a context layer directly into the query tower alongside user demographic features. Offline training utilized synthetic context derived from positive conversion labels paired with high dropout rates to preserve sequence reliance, while serving split into offline Transformer inference and online context computation. Offline evaluations showed a 3x to 10x increase in Recall@K, and production deployment lifted median candidate relevance by 275% to 300% and overall ROAS by approximately 0.7%.
Pinterest EngineeringSentry ·
Monitor Unreal Engine Game Performance with Application Metrics
Unreal Engine games frequently experience performance issues such as frame-rate drops, hitches, and network degradation that do not register as application crashes. To address the lack of live production telemetry, the Sentry Unreal SDK introduces automatic performance metrics. The integration periodically samples frame times, network health, active UObject counts, physical memory usage, and garbage collection pause durations across desktop, console, and Android platforms. Telemetry entries attach contextual hardware and environment attributes alongside trace IDs to connect aggregate latency spikes directly to underlying traces and spans. Enabled by default in Unreal SDK version 1.11.0, this telemetry provides developers with fleet-wide visibility into hardware-specific bottlenecks across game releases.
Ivan Tustanivskyi