FULL ARCHIVE
Follow the signal.
Browse every selected story by topic, beyond the twenty-item live edition.
INFRASTRUCTURE
60 STORIESINFRASTRUCTURE
Ontology-Driven Observability: Building an End-to-End Knowledge Graph at Netflix Scale
Netflix details a new observability architecture shaped by live streaming and massive concurrent traffic.
INFRASTRUCTURE
Proof-based general-purpose computing with Magnetar
Microsoft Research introduced Magnetar for proof-based general-purpose computing with standard-language support and speed gains.
INFRASTRUCTURE
Cloudflare and OpenAI: making AI discovery better for everyone
Cloudflare outlines a new OpenAI collaboration around AI discovery, freshness, and reducing wasted requests.
INFRASTRUCTURE
New: Sync real-time Stripe data to Postgres with Stripe Data Pipeline
Stripe introduced real-time Postgres sync for Data Pipeline to keep application databases current.
INFRASTRUCTURE
TimeSeries Tiered Storage Journey: Kafka/Flink Streams to Native Cassandra Cold Reads
Netflix shares two production designs for lowering hot-storage costs on multi-petabyte time-series data.
INFRASTRUCTURE
Behind the Scenes: Evolving Netflix’s Ads Event Pipeline for Live — Part II
Netflix describes rebuilding ads event enrichment for Live using stateful Flink joins.
INFRASTRUCTURE
Running Apache Spark experiments in my sleep (and on a plane)
Netflix just published a new production-scale Spark tuning case study from a pipeline migration.
INFRASTRUCTURE
Netflix Stratum Media Processing: Automated Container Right-Sizing
Netflix shared a new automation approach for right-sizing Stratum media-processing containers.
INFRASTRUCTURE
Reliable GPU compute for large training & inference jobs
Netflix published new details on GPU health, remediation, and fault tolerance for ML jobs.
INFRASTRUCTURE
From 2,500 requests to 24: Rebuilding star history without the stargazers
GitHub just published the architecture behind its new privacy-preserving star history API.
INFRASTRUCTURE
Your AI Isn’t the Problem. Your Infrastructure Is. — Jiachen Jiang, Coder
AI Engineer published Jiachen Jiang’s talk on infrastructure constraints in AI systems.
INFRASTRUCTURE
Rebuilding CI for AI-Scale Commit Volume — Gautam Korlam, SonarSource
Conference talk covers SonarSource’s CI changes for rising AI-driven commit volume and developer throughput.
INFRASTRUCTURE
Inside Hyperdrive: How we solved a rare Hyperdrive MySQL caching bug
Cloudflare details the fix behind Hyperdrive MySQL GA after tracing a 0.001% caching error.
INFRASTRUCTURE
Under the hood, off the hot path: How D1 scales to millions of databases
Cloudflare published new architectural details on D1’s control plane scaling to millions of databases.
INFRASTRUCTURE
Rewinding the exponential: How we keep hardware usage down
Cloudflare detailed pipeline changes used to reduce hardware growth while preserving data quality.
INFRASTRUCTURE
Announcing AWS Lambda Web Functions
AWS has announced Lambda Web Functions as a new serverless web application runtime option.
INFRASTRUCTURE
Filter, reshape, and redact logs before export with Transformers
Cloudflare announced Logpush Transformers for pre-export filtering, redaction, and reshaping of log streams.
INFRASTRUCTURE
From 15% to 90% GPU Utilization: Fix the Data Pipeline, Not the Model
A recent talk highlighting data pipeline bottlenecks as the main cause of poor GPU utilization.
INFRASTRUCTURE
Production Monitoring with Codex: Grafana, Kubernetes, & Security
OpenAI posted a new Codex operations video focused on monitoring, Kubernetes, and security.
INFRASTRUCTURE
Building Git infrastructure for agent-scale development
GitHub details an in-production Git infrastructure rebuild aimed at agent-scale software development.