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
From Spec-First to Enterprise-Ready: Extending GitHub Spec Kit
How presets, extensions, bundles, workflows, and governed catalogs make Spec-Driven Development adaptable at scale This article continues Spec-Driven Development: A Spec-First Approach to AI-Native Engineering, which int…
Agent Lightning v1.0: A 3,500-Line Lightweight Agentic RL Framework for Training Agents with Real Harnesses
Training AI agents with reinforcement learning can be challenging because their tools, context, and decision-making are managed by complex frameworks. Agent Lightning connects existing agents to RL training, making it ea…
Faster Scientific Image Analysis with NVIDIA cuPhoton
Observatories and telescopes, lasers and X-ray light sources, and other high-throughput instruments generate image data faster than CPU-bound pipelines can...
Beyond synthetic testing: Capturing and replaying real database workloads at Airbnb
How we capture real production database traffic at Airbnb and replay it offline to load-test, plan capacity, and de-risk upgrades. By: Zuofei Wang , Erluo Li Introduction At Airbnb, MySQL-compatible databases are a criti…
Expanding the Cyber Verification Program
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at…
All the numbers: Amazon Prime Day 2026 powered by AWS
Amazon Prime Day 2026 was exclusively for Prime members and ran June 23–26, 2026 with millions of deals across more than 35 categories. As part of our annual tradition of sharing how AWS powered Prime Day (2016, 2017, 20…
The keys to the Internet change on October 11. Are you ready?
On October 11, 2026, the DNS root switches to a new key-signing key (KSK-2024). Learn what this means for you, and how RFC 8509 trust anchor sentinels allow you to test whether your DNS resolver is ready for the rollover…
Multilingual Bridges: How Data Mixing Unlocks In-Language Reasoning
EmbeddingGemma 2: an open, lightweight multimodal embedding model
Discord Patch Notes: October 6, 2026
Check out the finer details of the more technical fixes implemented into Discord recently.
Building Git infrastructure for agent-scale development
We're rebuilding GitHub's Git infrastructure while GitHub keeps running, creating a foundation for agent-scale software development. The post Building Git infrastructure for agent-scale development appeared first on The…
Every artifact your teams ship, assembled right the first time
Every software build is assembled from open source packages, base images, and libraries, with your code on top. When one of those components is missing or has drifted, the build fails. At agent speed, those failures mult…
Dependency Firewall: Block risky packages before the build
Attackers disguise malicious packages as ones you trust. In June 2026, GitLab researchers found five malicious PyPI packages , four of them typosquats of Flask, Requests, and NumPy, that run at install time and steal CI/…
GitLab Transcend: Speed you can trust, all the way to production
At Transcend, we made over a dozen announcements across all four layers of our architecture for agentic software engineering: agent orchestration, data and context, DevOps workflows, and governance and security. Watch th…
Smarter personalization: How property data helps us understand user price sensitivity
Introduction Existing systems estimate user price sensitivity primarily from spending behavior or demographic proxies. They do not systematically account for residential property values, which can indicate a user’s finan…
Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the Nuance
NTS: Authenticated Time at Meta
Meta’s public time service now speaks NTS (Network Time Security, RFC 8915) at nts.meta.com. Packets are authenticated, so a device can verify the time came from us and was not modified on the way. Our NTS servers hold n…
Build Azure canvases with the Canvas authoring plugin
Learn how the Canvas authoring plugin helps you build Azure canvases with Microsoft Canvas Toolkit, from a read-only starter to a working app you can inspect, test, and adapt. The post Build Azure canvases with the Canva…
What is Agent Experience (AX)?
Your agent says it's done, and the code compiles, but did it pick your technology? Did it use it correctly? Learn what Agent Experience (AX) is, how to measure it, and why the obvious fix isn't always the right one. The…
Introducing Mistral Large 4
What AI gets wrong and what failure teaches us
Jennifer Neville did not want to go into computer science—but that’s exactly where she landed. Neville discusses the starts and stops that led to her professional sweet spot and her work identifying “surprising failures”…
Metrics Board: Building an Agent-ready Metrics Layer
Michele Ceccacci; Software Engineer I | Jason Coffman; Sr. Software Engineer | Colm O’Shaughnessy; Software Engineer II | Laura Palmer; Staff Product Manager | Adam Podraza; Manager, Engineering | Surya Karri; Manager, E…
Negotiating Ontological Boundaries in User-Authored Personal Sensing Systems
Designed artifacts are ontological, shaping, and at times limiting, what becomes possible or imaginable. One path toward mitigating such foreclosures is giving people power over how systems are designed and built. Despit…
AWS Weekly Roundup: Amazon Bedrock Managed Agents powered by OpenAI, Q3 service availability updates, Kiro workflows, and more (October 5, 2026)
Last week, we announced a public preview of Amazon Bedrock Managed Agents powered by OpenAI, built on a customized version of OpenAI’s Agents API engineered to be AWS-native and integrated with AWS resources. You can now…
Everything we launched during Birthday Week 2026
We celebrated our 16th birthday with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades. Here’s a day-by-day roundup of everything we shipped.
One year later: the power of 1.1.1.1 interns
A year after announcing our goal to hire 1,111 interns, more than 750 early-career builders have shipped real products across 48 teams at Cloudflare. From Birthday Week launches to post-quantum security, our interns prov…
Cohere and PwC partnership announcement
North 2: Enterprise AI Without Compromises
ReviewBench: An open benchmark for AI code review
We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics. The post ReviewBench: An ope…
Two front doors: Module-level access in a Django GRC app
GitLab s engineering team builds a lot of our own internal tooling, but one platform in particular forced us to rethink how we handle authorization: our internal GRC tool that serves two very different customer bases und…
Powering AI-led research through simulation
The short story Consider a Friday evening. A food order arrives from a mall in the city center. One driver is nearby; another is finishing a drop-off and will be available shortly; a second order from the same mall may o…
AI Agents Need Memory: Building Persistent Memory for Agentforce
By Roopang Chauhan, Sundar Vedula, Peng-Wen Chen, and Nikhil Bojja. In our Engineering Energizers Q A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Roopang Chauhan,…
The Agent Said It Was Done. The Database Disagreed.
Claude Frontier Academy: $100M to train 10,000 engineers
Language Discrimination Improves Linguistic Learning in Multilingual Speech Models
Multilingual self-supervised speech models can benefit from sharing information across languages, but under a matched total pretraining data budget they still fall short of monolingual models. We show that strengthening…
Limits of Confidence in Diffusion
Discrete diffusion, including remasking and uniform-state samplers, generate a sequence by writing multiple token positions per step, drawing each from a per-position distribution and choosing which positions to write fr…
Follow the thread: a new dashboard to investigate account abuse
Fraudsters are increasingly using AI to bypass stateless security checks. Cloudflare's new Account Abuse Protection dashboard uses stateful analysis and edge-generated Hashed User IDs to help teams investigate and block…
Announcing Cloudflare OHTTP Gateway – expanding access to Cloudflare’s privacy-preserving infrastructure
We’re announcing the closed beta of a self-serve Cloudflare OHTTP Gateway. We’re also renaming our Privacy Gateway to Cloudflare OHTTP Relay to better distinguish the two products.
Building for good: How civil society organizations are automating on Cloudflare
Some of the world's leading organizations are building the future of non-profit work with Cloudflare.
Introducing Cloudflare Traces: follow requests through our entire platform
Cloudflare Traces shows how a request moves through security rules, transformations, cache, routing, Workers, and your origin, then follows it across services running anywhere in your stack.
Updates on our pledge to make Cloudflare features accessible to everyone
A year after pledging to eliminate two-tier product access, Cloudflare has expanded Logpush, multi-account governance, and higher platform limits to all accounts. Here is an update on our progress, how we dogfood these t…
Introducing Web Search API via AI Gateway
Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI Gateway, REST APIs,…
2026 Birthday week: network performance update
Cloudflare now ranks as the fastest provider across 74% of the top 1,000 global networks. By incorporating background telemetry from Cloudflare Challenge Pages, we have expanded our real-user measurement scale while main…
8 major updates to Cloudflare Observability
Cloudflare is launching eight major updates that bring logs, traces, analytics, alerts, dashboards, querying, and telemetry export into one observability platform, with simpler and more predictable pricing.
Protected Quick Tunnels: simple accountless authentication for your next dev project
Quick Tunnels now support email authentication. Add --allowed-mail to one cloudflared command, and only the addresses or domains you list can reach your local app. No Cloudflare account required on either side.
AI is changing developer work. Here are three skills to strengthen.
Learn to direct AI agents, critically review their output, and keep technical judgment at the center of your workflow. The post AI is changing developer work. Here are three skills to strengthen. appeared first on The Gi…
DeepSeek-Reasonix: How a poisoned config can hijack an AI coding agent
GitLab s Threat Research Group discovered a command execution vulnerability ( GHSA-grg2-7gc6-36m6 , CVE-2026-102437 ) in DeepSeek-Reasonix Studio, a desktop git client designed for developers pairing with AI coding assis…