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
Discord Patch Notes: September 8, 2026
Check out the finer details of the more technical fixes implemented into Discord recently.
Bring your own model to GitLab Duo Self-Hosted with Microsoft Foundry
For many organizations, the question about AI coding tools isn t whether they help, but where the code goes. Teams under data sovereignty, residency, or regulatory constraints need to know which network handles their sou…
How Metadata and Runtime Telemetry Reveal Which Enterprise System Problems to Fix First
By Karishma Lalwani, Anand Vardhan, and Sanjeevani Bhardwaj. In our Engineering Energizers Q A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Karishma Lalwani, Vice P…
Why Spotify Is Not Using Bayesian A/B Testing
Clearing the confusion about what Bayesian A/B testing is. The post Why Spotify Is Not Using Bayesian A/B Testing appeared first on Spotify Engineering .
Introducing Claude Design by Anthropic Labs
AWS Weekly Roundup: Claude Fable 5.1 on AWS, Amazon Linux 2027 preview, AWS Certified AI Business Strategist, and more (September 7, 2026)
Last week, Claude Fable 5.1 became available on AWS. According to Anthropic, Claude Fable 5.1 delivers frontier intelligence for ambitious tasks across coding, scientific research, and enterprise workflows. Claude Fable…
Formalizing Fermat's Last Theorem
Aidan Peppin
Project HydraFusion: Frontier quality via multi-model orchestration
In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated workflow cost. Now available as a research preview in GitHub Copilot.…
Dana Arsovska
Automation’s Early Footprint: The ATE Dataset
Introducing WeatherNext 3, our most advanced and accurate global weather AI model
GitHub Copilot app for Beginners: Run several agents at once
Learn how to run parallel agents in the GitHub Copilot app, and experience the moment it stops feeling scary and starts feeling powerful. The post GitHub Copilot app for Beginners: Run several agents at once appeared fir…
Agentic Machine Learning Modeling at Instacart
Tilman Drerup, Moe Moazzami, Shih-Ting Lin, Greg Reda (and many more) Introduction At Instacart, artificial intelligence is fundamentally changing the way our machine learning engineers operate. In a prior blog post , we…
ZGateway: Learnings from Putting a Proxy in Front of ZippyDB
We’re introducing ZGateway, the proxy we are using to unify traffic through ZippyDB, Meta’s most widely-used key value store. As a bonus, it also enables admission control, load balancing, cross-region resilience, and ri…
How Agentforce Achieves 100% Deterministic Rendering for AI Agent UX
In our Engineering Energizers Q A series, we highlight the engineering minds driving innovation across Salesforce. Today, we spotlight Abhi Rathna, Product Management Director for Agentforce, whose team tackled a fundame…
Portal by Spotify cut my Claude Code token usage by 90%
Most of what an AI coding agent does for me isn't thinking. It's I/O. The post Portal by Spotify cut my Claude Code token usage by 90% appeared first on Spotify Engineering .
REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs
Most current vision-language-action (VLA) models—such as OpenVLA, π0, RT-2, and RDT-1B—are “monolithic.” This means they generate raw motor commands or very short sequences of actions, without organizing behaviors into r…
The Benefits of Small Language Models (SLMs)
Introducing Gemini 3.8 Flash and 3.8 Flash Cyber
Proactive cyber defense for governments and enterprises
Decoding the new AI lingo: Loops, harnesses, squads, hill climbing… oh my!
From loop engineering to harnesses, squads, and open weights, the GitHub Podcast breaks down the AI terms showing up in developer conversations. The post Decoding the new AI lingo: Loops, harnesses, squads, hill climbing…
How we make AI coding more cost efficient without sacrificing task quality
Why shorter outputs can cost more, and how GitHub Copilot reduces wasted work across the complete coding task. The post How we make AI coding more cost efficient without sacrificing task quality appeared first on The Git…
An Organizational Second Brain: Building an AI That Learns From Experts
We’ve built an AI agent that acts as a secondary expert for a given domain, making deep specialist knowledge readily available and preserved for anyone in an organization to access, share, and build upon. This is not a t…
Developing Enterprise Frontier Safeguards with our customers
Developing Enterprise Frontier Safeguards with our customers
Developing Enterprise Frontier Safeguards with our customers
Claude Fable 5 and Claude Mythos 5
Introducing agentic video understanding with Gemini
Becoming an AI Team
John Grass | Sr. Manager, Engineering A Fundamental Transformation An AI team is fundamentally more than just a group whose members incorporate AI tools into their existing workflows. The journey to becoming an AI team n…
Improving our alignment and security practices
Improving our alignment and security practices
Amazon EC2 R9g and R9gd instances powered by AWS Graviton5 processors are now generally available
Amazon EC2 R9g and R9gd instances powered by AWS Graviton5 are now generally available, delivering up to 25% better compute performance than R8g, ideal for databases, in-memory caches, and real-time analytics.
AWS Weekly Roundup: Welcome DuckLabs to the team, Agentic Resource Discovery (ARD), and more (August 31, 2026)
The news that interested me the most last week was the DuckLabs acquisition. AWS has signed a definitive agreement to acquire DuckLabs, the Amsterdam-based company behind DuckDB, the popular open source analytical databa…
Testing cookie behavior across hundreds of web surfaces with our in-house auditor
Our cookie auditor acts like a privacy-conscious user by visiting web pages and checking that they only load cookies consistent with that user’s preferences.
Rerouting the Stream: How Lyft Moved to the Apache Flink Kubernetes Operator
Written by Maheep Myneni , Arda Kuyumcu , and Prem Santosh Udaya Shankar at Lyft. Why We Migrated : Technical Debt Meets Modern Streaming Demands Over the past several quarters, Lyft’s Streaming Compute team retired our…
GigaPath-Flash and GigaTIME-Flash: Toward population-scale discovery with efficient pathology foundation models
What if pathology foundation models could do more with less? GigaPath-Flash and GigaTIME-Flash cut computational demands while maintaining strong performance, opening the door to larger studies and broader exploration. T…
Why AI Agents Get the Right Facts but the Wrong Answer—and How GraphRAG Helps
By Sivakumar Shanmugam and Indrojit Deb.An AI agent rejects a valid customer return. You check its citation: the policy really does say 90 days. You check the purchase: it falls outside that window. Both facts are correc…
Agent Seer: Synthesizing Scenarios from Specification Understanding
Evaluating AI agents that use external tools requires realistic test scenarios that capture how practitioners compose tools and iterate across conversation turns. Constructing such scenarios by hand demands deep domain e…
LLMs Are Not (Consistently) Bayesian: Quantifying Internal (In)consistencies of LLMs’ Probabilistic Beliefs
Modern AI systems are being deployed in complex domains such as medicine, science, and law, where there is often not a single correct answer given the observed evidence. Such systems must be able to represent and update…
Generative AI for business: Use cases, benefits, and adoption
Data Mesh at Grab (Part III): Operationalizing data reliability with automated DPIs
Introduction In the first two parts of this series , we described how Grab approaches data mesh through the Signals Marketplace: a way for teams to publish, discover, and reuse trusted data products across domains. Part…
MAPS: Netflix’s Multimodal Asset Personalization at Scale
By Emma Yanyang Kong , Aditya Deshpande , Asad Abbasi , Bowei Yan , David Fagnan , Ashish Rastogi , Dhaval Patel , Ray Zhang Introduction The Netflix experience is a journey of discovery. Every visual cue, from the artwo…
How AI-Powered Attacks Led Salesforce to Reinvent Hyperscale DDoS Defense
In our Engineering Energizers Q A series, we spotlight the engineering leaders driving innovation across Salesforce. Today, we meet Herman Kwong, EVP of Software Engineering, whose team developed DREAM (DDoS Response and…
Expanding our support for scientists
Previewing the Model Hardware Standard
Previewing the Model Hardware Standard
Expanding our support for scientists
From Preferences to Principles: Rubric-Based Alignment for Grounded Knowledge Answers
Designing effective reward signals for open-domain question answering is challenging because high-quality responses must simultaneously satisfy multiple aspects of answer quality that are difficult to capture with a holi…