I’m calling it now, the adoption of AI agents into software development will be one of the most costly mistakes in the field’s history. Agents cannot program, and it’s taking longer and longer to realize that they can’t. They are a highly sophisticated statistical model designed to mimic the distribution of programming. The output is broken, but in a way that’s getting harder and harder to detect. Which is exactly what you’d expect from an increasingly accurate statistical model.
Why AI hasn’t replaced software engineers, and won’t
Coding agents as normal technology
AI should help us produce better code - Agentic Engineering Patterns
AI should help us produce better code - Agentic Engineering Patterns
The AI Industry Has a Major Problem: Most People Aren’t Freaks Who Want an AI Agent Running Their Whole Life
There's a problem for AI agents like Meta's Muse: ordinary people don't seem very interested in what they're offering.
The New Software Lifecycle
I co-wrote a Google whitepaper about how AI is changing the software lifecycle. I'm not going to summarize the whole thing. Instead, here are the handful of ...
More Than a Tool
What We Learned from a Year of Conversations About AI
The 80% Problem in Agentic Coding
Managing comprehension debt when leaning on AI to code
Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question unanswered: does the structural and stylistic quality, or ``cleanliness'' of the underlying code affect an agent's ability to navigate and modify it? To isolate the effect of code cleanliness from agent capability, we introduce an evaluation protocol built around minimal pairs: repositories that match on architecture, dependencies, and external behaviour, but differ on static-analysis rule violations and cognitive complexity. The pairs are constructed in both directions, by agent pipelines that either degrade a clean repository or clean a messy one. We author 33 tasks across six such pairs, evaluated through hidden tests at the application's public surface. Across 660 trials with Claude Code, code cleanliness does not change the agent's pass rate. However, it substantially alters the agent's operational footprint: agents working on cleaner code use 7 to 8% fewer tokens and reduce file revisitations by 34%. Our findings suggest that traditional maintainability principles remain highly relevant in the era of AI-driven development, shaping the computational cost and navigational efficiency of coding agents. Code cleanliness joins model choice, harness, and prompting as a factor that materially affects agent behaviours.
Programming (with AI agents) as theory building
Back in 1985, computer scientist Peter Naur wrote “Programming as Theory Building”. According to Naur - and I agree with him - the core output of software engineers is not the program itself, but the theory of how the program works. In other words, the knowledge inside the engineer’s mind is the primary artifact of engineering work, and the actual software is merely a by-product of that.
AI Tools Accelerates Coding, but Not Overall Software Delivery, GitLab Research Finds
GitLab's 2026 AI Accountability Report highlights an AI Paradox: although 78% of developers say they code faster, overall software delivery has not accelerated due to downstream testing and review bottlenecks and new challenges for enterprise governance and traceability.
Where is all the new, good software?
Here's a question we see, especially from AI skeptics: if AI coding is so great, shouldn't we be seeing more new, good software by now? Here are some answ...
The 8 Levels of Agentic Engineering — Bassim Eledath
AI's coding ability is outpacing our ability to wield it effectively. That gap closes in levels — 8 of them. Here's the progression from tab complete to autonomous agent teams.
Is AI causing a repeat of Frontend’s Lost Decade? | Mastro Blog
AI is doing to programming what framework-brain did to the frontend before. Deskilling, or just working at a higher level of abstraction?
Why AI hasn’t replaced software engineers, and won’t
Arvind Narayanan and Sayash Kappor take on the question of AI job losses through the lens of a profession that is uniquely suited to AI disruption - software engineering. In …
The Future of Software Engineering Isn’t What You Think
Over the past two decades, I’ve watched software eat the world, then hardware catch up, then Generative AI reshape both at the same time…
What spec-driven development gets wrong
The most powerful AI software development platform with the industry-leading context engine.
Labor market impacts of AI: A new measure and early evidence
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.