Reading room.
Engineering blogs & AI research
A reading room from engineering teams and AI labs: titles, short feed excerpts, and links to the originals. For my own essays, explore the writing archive.
- 1359 articles tracked
- 37 sources
- Refresh scheduled daily
Sources
GitHub’s model for secret detection: Finding more secrets with less noise
GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86%. The post GitHub’s model for secret detection: Finding more secrets…
GitLab's agent orchestration eliminates the wait between development stages
AI coding tools have changed how fast software gets written, but not how fast it ships. As code generation accelerates, the bottleneck moves downstream into verify, review, and ship. Those stages still run on human time.…
Make every AI credit count: See, cap, and reduce agent spend
Costs multiply with every task you hand to an agent. Each task consumes tokens and credits, and as agents spread across your teams and automations, consumption can grow faster than usage. If you run the platform, you own…
Scaling Git for the agentic software factory
AI agents are fundamentally changing the economics of software development. As the cost of producing code falls, the volume of changes moving through the software factory is accelerating beyond what infrastructure design…
GrabMart data for faster disease outbreak detection
Abstract Retail purchases can supplement clinical surveillance because changes in demand for some over-the-counter (OTC) products may appear before confirmed case reports. This article describes an early-stage concept fo…
Run fast, private agents on-device with LFM2.5-24B-A2B
Meta’s Generative Ads Model (GEM): Scaling the Central Model and Compute Engine for Frontier Ads AI
Last year, we introduced GEM, the industry’s largest recommendation system (RecSys) foundation model. GEM established Meta s first LLM-inspired paradigm for ads recommendation, driving major performance gains. Building o…
NVIDIA Run:ai Is Now Open Source as Part of NVIDIA DSX AI Factory Platform
NVIDIA is making the full NVIDIA Run:ai platform available as open source software, giving customers, developers, and ecosystem partners access to...
How to Rewrite Apache Spark UDFs for GPU Acceleration with AI Agents
Enterprise applications have become increasingly demanding. Agentic AI has compounded the need for vast amounts of enterprise data with frequent, complex...
The “alien” economics of AI monetization
As usage, costs, and customer expectations change, AI companies are moving beyond traditional SaaS pricing. Leaders at Monetize 2026 shared how they’re combining subscriptions with usage-based billing, building spend con…
Strengthening our defenses against distillation attacks
Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
The increasing demand for GPU-accelerated machine learning inference has exposed limitations in centralized GPU infrastructures, including high cost, limited elasticity, and long wait times under resource constraints. At…
Large Language Models for Machine Translation Quality Annotation: Humans and Models Are Both Challenged
Large Language Models (LLMs) are considered to be a more efficient and cost-effective alternative to human judgment for Machine Translation (MT) evaluation. With MT evaluation spanning a large number of language pairs, d…
Self-Compacting Language Model Agents
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing scaffolds mitigate it with fixed-interval co…
Announcing AWS Lambda Web Functions
AWS Lambda Web Functions is a serverless compute primitive that runs your HTTP framework natively, delivering fast, consistent responses through multi-concurrent execution and automated global distribution.
Filter, reshape, and redact logs before export with Transformers
Logpush now supports Transformers, allowing teams to filter, redact, and reshape log streams using SQL before export. Powered by Apache DataFusion and Apache Arrow, Transformers apply those changes directly to log data b…
GitHub Copilot app for Beginners: How to teach Copilot about your codebase
Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright. The post GitHub Copilot app for Beginners: How to teach Copilot about your codebase appeared…
GitLab Critical Patch Release: 19.4.2, 19.3.4, 19.2.8
Turning Opportunistic AI Inference Capacity Into Better Ads Recommendations
At Meta, we’ve built a system that enhances ads recommendations by leveraging idle inference capacity in our fleet. Two elasticity levers in the system allow ads recommendation work to expand across opportunistic capacit…
OCP Summit 2026: Powering AI with Open Innovations in Scale-Up, Scale-Out, and Scale-Across Networks
At the 2026 Open Compute Project Global Summit, Meta is sharing the next generation of open networking infrastructure, including: Our first liquid-cooled network rack (IcePack), and 102.4T switch platform (IceCube). Flat…
Shipping Media Over QUIC at Meta Scale for Instagram Live Ingest
Meta has begun deploying Media over QUIC (MoQ), an emerging open protocol for real-time video streaming at scale. MoQ will help simplify our protocol stack for live streaming video and enhance overall user experience for…
Simulating student learning for better AI tutoring
StudentSim is a research system for evaluating and improving AI tutoring tools before they are tested with learners. It models how individuals may engage with tutors, giving feedback to improve tutor performance across s…
ReplaySSM: Rethinking State Storage for Faster Hybrid-Model Decoding
Hybrid models interleave state-space model (SSM) layers with a few attention layers. NVIDIA Nemotron 3, Qwen3.5 through Qwen3.8, Kimi-K3, and GLM-5.3-Flash are...
Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
We are expanding the Clef decision model family with Clef-omni, natively processing audio, video, images, and text in a single pipeline. We’ve also lowered Clef-flash pricing and boosted Clef inference speeds by up to 2.…
Deno is joining Cloudflare
The Deno team is joining Cloudflare to radically simplify self-hosting Workers and Durable Objects, so developers can use the same primitives in more places.
Introducing on-demand CPU and memory profiling with flamegraphs for Workers and Durable Objects
On-demand CPU and memory profiling for Cloudflare Workers and Durable Objects is now available. Now you can generate interactive flamegraphs directly in production to quickly track down memory leaks and performance bottl…
Shared vs. Dedicated AI Inference: Embed & Rerank
Hack the World: Why hackathons are still the best place to learn to build
The barriers to building software have collapsed. Today, anyone can build. Hackathons are a great place to start learning. The post Hack the World: Why hackathons are still the best place to learn to build appeared first…
Impactful scheduling for GPU clusters
Introducing the Agent Experience (AX) Practitioner Playbook
AI coding agents now pick the SDK, the version, and the pattern for your developers. The AX Practitioner Playbook is our method for finding out whether they get your technology right, and for fixing the sources they rely…
From Activity to Intent: Generating User Journeys with LLMs
Lin Zhu | Sr. Staff Machine Learning Engineer; Manan Kalra | Machine Learning Engineer II; Byung Eun Jeon | Sr. Machine Learning Engineer; Ye Liu | Staff Machine Learning Engineer; Xiangyi Chen | Sr. Machine Learning Eng…
Building on our commitment to American scientific discovery
Introducing the Anthropic Cyber Mission
2026 Usage Policy update
Normalizing Trajectory Models
Diffusion-based models decompose sampling into many small Gaussian denoising steps, an assumption that breaks down when generation is compressed to a few coarse transitions. Existing few-step methods address this through…
Bridging technical depth and usability: The story behind Radar’s redesign
We redesigned Cloudflare Radar to make real-time global traffic and outage data accessible to a wider audience — including journalists, less technical researchers, and everyday users. By introducing an interactive map an…
Bridging technical depth and usability: The story behind Radar’s redesign
We redesigned Cloudflare Radar to make real-time global traffic and outage data accessible to a wider audience — including journalists, less technical researchers, and everyday users. By introducing an interactive map an…
Cohere Expands Canadian Footprint with New Ottawa Office
How one bug bounty researcher chooses the features they investigate
As we kick off Cybersecurity Awareness Month, the GitHub Bug Bounty team spotlights @vaib25vicky, exploring their methodology, techniques, and experiences hacking on GitHub. The post How one bug bounty researcher chooses…
Track organization-wide security risk in one dashboard
If you run application security across more than one top-level group, getting a single organization-wide view of your risk has meant manually pulling together data. That is operational work rebuilt in spreadsheets and on…
The model that didn't exist, so you made it yourself
5 Steps to Create SimReady Assets for Robotics with Frontier AI Models
Preparing CAD assets for robotics simulation requires more than converting geometry to OpenUSD: developers must configure and validate materials, collision...
Building Reliable Data Analytics Agents: Lessons from the KDD Cup
The NVIDIA KGMON team placed second in the KDD Cup 2026 Data Agents competition with a system built around a simple idea of making an agent's harness smaller,...
Apache Spark Resource Optimization: Lessons From Eight Million Jobs a Day
By Siddharth Sharma, Suvhrajit Basak, Kusum Dhalia, and Nabeel Qaiser. Your compute bill keeps climbing, and your Spark workloads keep succeeding. Successful execution tells you the configuration worked. It does not tell…
Introducing: Spotify Technology. Proven at Spotify, now yours.
Introducing Spotify Technology. The post Introducing: Spotify Technology. Proven at Spotify, now yours. appeared first on Spotify Engineering .
Building an evidence-grounded agentic security operations harness on Cloudflare
Cloudflare Managed Defense uses a team of specialized AI agents built on Workers and global network telemetry to analyze security alerts. By separating deterministic evidence collection from model inference, the system d…
Secret protection must scale with software
Developers aren’t becoming more careless; they’re being outpaced. The tools that let developers create more software should also take on more of the work of protecting it. The post Secret protection must scale with softw…