The Curious Engineer

Every

2026

150 posts

2026 150

October 2026

  1. Vibe Check: Duet—Anthropic's Always-on AgentAnthropic’s personal agent is the first one we’d call a pro tool, even with the plumbing still unfinished
  2. Source Code
  3. Why We Replaced Personal Agents With One for the Whole Company
  4. Playtesting
  5. We Caught an AI Cheating by Watching It Play ‘StarCraft’
  6. Context Window
  7. Codex’s Comeback Up Close
  8. Context Engineering Is Knowing When to Start Over
  9. How Codex HappenedInside OpenAI’s comeback in coding, from a failed launch to the app that took over ChatGPT
  10. 🎧 The Best Founders Have Something AI Can’t Tell Them
  11. Vibe Check: Gemini 4 Argon Puts Google Back On the Frontier
  12. One Agent for the Whole Company
  13. You Already Signed This Off (In the Simulation)
  14. Why We Handed Our Agent’s Infrastructure to Anthropic
  15. Building a More Efficient Agent
  16. Introducing the Every AgentAn agentic coworker in Slack built to be the fastest way to AI-pill your company
  17. When Trying to Make AI Better Makes It Worse
  18. ChatGPT Wants to Be Your Operating System
  19. How to Get Better at AI by Asking AI

September 2026

  1. 🎧 How Sam Altman Uses Dots to Take Back His Time
  2. Vibe Check: OpenAI DevDay 2026With 20-plus launches, here are the five that matter
  3. Vibe Check: Dots—Always-on Agents in ChatGPT
  4. Vibe Check: Sonnet 5.5 Finds Its Place in Claude’s Crowded Family
  5. Opus 5.5 and Sol Split the Team
  6. Copilot Gets a Seat in the Org Chart
  7. Why Evals Are So Hot Right Now
  8. How to Get the Most Out of Jev
  9. Good Writing With AI Starts Before the Prompt
  10. Vibe Check: GPT-6 Sol vs. Opus 5.5
  11. Vibe Check: Opus 5.5 Is Pulling Our Codex Converts Back to Claude
  12. How to Create Your Own Personal AI Benchmark
  13. Copy Our Homework
  14. Vibe Check: Is Astra a Breakthrough for Indie Filmmakers?
  15. Why You Should Burn More Tokens
  16. Show Us Your Folders
  17. 13 Beliefs About AI Writing
  18. Mini-Vibe Check: TypeSafe's Jev Judged Everything I’ve Written in 0.7 Seconds
  19. You're Probably Sleeping On Computer Use
  20. What Playing With AI Taught Me About My Work
  21. What to Make of the Anthropic Warning
  22. What I Learn When I Run Out of AI
  23. Evals for Everyone
  24. What Writers Who Use AI Want You to Know
  25. To Read—Or Not to Read the Code?
  26. A Split Verdict on Fable vs. Astra
  27. The Folder Is the Agent
  28. Vibe Check: GPT-6 Astra Is a Big Upgrade With Some Bad Habits
  29. 🎧 How an Every Staff Writer Developed Compound Writing
  30. Vibe Check: Fable 5.1—Anthropic Is So Back (Again)

August 2026

  1. What We Learned From 15 Hours of Anthropic Certification Training
  2. Our Agents, Ourselves
  3. 33 Questions Executives Ask About AI—Answered
  4. Our ChatGPT and OpenClaw Guides Just Got an Overhaul
  5. The Case for Cloning Your Coworkers
  6. Benchmarks Don’t Know Your Job
  7. I Tried the AI Model Built to Fix AI Writing
  8. Life After Automation
  9. The Healthcare Company That Built the AI Tool It Couldn’t Buy
  10. In Defense of AI Writing
  11. An Engineering Team for the Cost of Codex
  12. What Does Human Work Look Like After Automation?
  13. Our AI Costs Jumped 230 Percent. I’m Not Setting Token Budgets—Yet.
  14. The Next Era of Great Work
  15. Introducing Thesis: 2027
  16. Agents Find a Way
  17. Agents for Hire
  18. I Vibe Coded a Security Risk
  19. Your AI Is a Mirror of How You Think
  20. Designing With AI? Make a Jig.
  21. A Codex of One’s Own
  22. Mini-Vibe Check: ChatGPT Voice Mode
  23. To Stay Ahead in AI, Think Like a Designer
  24. The Best AI Agent Builder Is Trapped Inside Microsoft
  25. Your AI Is a Team of Specialists

July 2026

  1. Fable as CEO
  2. What If Slack Was Your AI Command Center
  3. Taming Opus 5
  4. Three New Habits for the Age of AI
  5. Inside OpenAI’s Race to Reinvent Software Development for the Agent Era
  6. Sometimes You Have to Delete Everything
  7. Vibe Check: Claude Opus 5 Is Brilliant in Flashes, Frustrating in Practice
  8. How Every's Team Used AI to Ship Its Biggest Launch Ever
  9. Drowning in Demos? Here’s a Better Way to Prototype
  10. Why Some AI Workflows Stick—And Others Don’t
  11. The Model Is the Easy Part
  12. I'm an Editor—And I Built Our Newest Feature
  13. The Case Against Skills
  14. The Ops Team That Routes Work Across Models
  15. Introducing Every All Access
  16. The Urge to Merge (ChatGPT and Codex)
  17. How I Polish Software That Agents Built
  18. From Doing to Tending
  19. How GPT-5.6 Changes Knowledge Work
  20. Welcome to Efficiencymaxxing
  21. Use Fable Before You Know What to Ask
  22. A Tale of Two Models
  23. Vibe Check: Sonnet 5—A Model Pitched for Everyone Impresses No One
  24. Codex in Practice

June 2026

  1. Your AI Strategy Is Making Bets. Do You Know Which Ones?
  2. AI Could Do Anything. Then It Met PowerPoint.
  3. Everyone Gets an Agent. Almost No One Gets the Model.
  4. Claude Code Is the OpenClaw Alternative You Already Have
  5. Codex for Everything and Everyone
  6. Can AI Learn Good Judgment?
  7. Token Tightening
  8. I Asked an AI to Audit My Own Career
  9. Built on Moving Ground
  10. How Anthropic Makes Claude More Reliable
  11. Loops for Non-coders
  12. We Built Our Own Agent-native Tool. It Overhauled How We Build Software.
  13. I Interviewed an AI Version of GitHub’s COO—Then Spoke to the Real One
  14. Fable, Disabled
  15. The Moral of Fable
  16. AI Everywhere, All at Once
  17. How to Get the Most Out of Fable 5
  18. My Editor Caught Me Sounding Like AI. Now AI Catches Me First.
  19. AI Is Ready. Organizations Aren’t.
  20. How Microsoft Is Building for a World of Metered Intelligence
  21. Why We’ll Still Be Employed When AI Can Do Everything
  22. Spiral 4.0 Goes Agent-native
  23. Opus 4.8 Is Smart Enough to Get in Your Way
  24. Where Do You Fall on the Eight Levels of AI Adoption?
  25. Company-wide AI Implementation in Five Steps

May 2026

  1. How We Work Now
  2. Compound Engineering Gets an Upgrade
  3. Vibe Check: Opus 4.8—Anthropic Should’ve Rounded Up to 5
  4. How to Use Codex for Knowledge Work: A Power User’s Guide
  5. Cheap Competence, New Frontier
  6. Notes From the Foothills of the Singularity
  7. After Automation
  8. Google I/O: Agents, Agents, Agents
  9. Inside the 100-agent Software Factory
  10. How to Start a Career When AI Is Doing Your Entry-level Job
  11. After the Personal Agent
  12. We Gave Every Employee an AI Agent. Here's What We're Doing Differently Now.
  13. Opus 4.7 Reels Us Back In
  14. Mining Your Life for Context
  15. The Fallacy of the 16-hour Agent
  16. Socrates as a Service
  17. AI Work Is Splitting in Two
  18. The Culture of AI Engineering
  19. Inside Anthropic’s 2026 Developer Conference
  20. OpenAI Flips the Script
  21. The Dawn of Codex-native Apps
  22. I Let ChatGPT Manage My Workweek
  23. Codex Goes to Work
  24. Claude Code for Product Managers

April 2026

  1. Who Isn't Using GPT 5.5
  2. Compute Is the New Cash
  3. One App to Rule All Knowledge Work