I let Claude review my PRs: What it caught and missed
Anthropic’s own data puts code output per engineer at 200% growth after internal Claude Code deployment. Review throughput didn’t scale
Mira Murati’s Thinking Machines Lab Makes The Technical Case For Human-Centered AI Built On Customizable Model Weights
Thinking Machines Lab published a report to build AI that extends human will and judgment. Most AI in use today
CI/CD with Robert Erez – by Gergely Orosz
Listen and watch now on YouTube, Spotify, and Apple. See the episode transcript at the top of this page, and
Amazon ECS introduces new high-resolution metrics for faster service auto scaling
Amazon Elastic Container Service (Amazon ECS) service auto scaling automatically adjusts task counts to meet workload demand with comprehensive scaling
Sunsetting Create React App – React
February 14, 2025 by Matt Carroll and Ricky Hanlon Today, we’re deprecating Create React App for new apps, and encouraging
Context Windows Are Not Memory: What AI Agent Developers Need to Understand
In this article, you will learn why a large context window is not the same thing as agent memory, and
May 2026 Jobs Report: One Strong Headline, but Two Realities
A surprising 172,000 jobs added in May tells one story; the frozen hires rate and the unemployed waiting longer for
IBM and Red Hat Launch Lightwell Catalog to Automate Remediation
IBM and Red Hat this week revealed that Lightwell Network, a catalog of more than 6,500 application-layer dependencies that drives
Springs and Bounces in Native CSS • Josh W. Comeau
Introduction When creating animations, we can decide how to transition between states using a timing function. Historically, we’ve used Bézier
Long Context Isn’t Free — I Built a Safe Prompt-Pruning Layer That Makes LLM Systems Work
I’ve worked on, conversation state tends to grow quickly over time. It’s common to resend large portions of the history