Engineering management after the cost of code collapsed

Nothing works and everyone is euphoric

Kimi K3 exploited the latest Redis server

Why Software Factories Fail (or: harness engineering is not enough)

Code mode yields a 99.2% cost reduction in our systems

AI Agent – TRMNL

Claude Is Not a Compiler

Codex is wearing out our devices

Annoying and alarming things about OpenCode

Claude Code uses Bun written in Rust now

OpenAI reduces Codex Model Context Size from 372k to 272k

What AI did to stackoverflow in a graph

A grumpy screed about AI in software engineering

Claude Code: Anatomy of a Misfeature

Kimi K3 is now #1 in the Front end Code Arena with 1679 pts, surpassing Fable 5

Agent-talk: Enabling coding agents to work together

Open-source memory for coding agents, synced over SSH

DSLs Enable Reliable Use of LLMs

The Agentic Loop: Three loops in a trench coat

Proof of care in the age of AI

How to stop Claude from saying load-bearing

Claude is just Mr. Meeseeks

A Study of Microsoft's Early 2026 Rollout of Claude Code and GitHub Copilot CLI

Fable extended until 19 July

Old and new apps, via modern coding agents by Terry Tao

Why Write Code in 2026

Write code like a human will maintain it

GPT-5.6

Opinionated and easy Pi.dev configuration

AI changes the economics of software rewrites

We made Grok 4.5, GPT-5.5, and Claude build the same apps

We charge $10k a week to delete AI-generated code

Automating AI Away

YC CEO says he ships 37K LoC AI code per day. A developer looked under the hood

The Making of Claude Code

GPT-5.6 Sol Ultra will be in Codex

sqlite-utils 4.0rc2, mostly written by Claude Fable (for about $149.25)

GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance

AI has torched the market for junior programmers

Agentic coding notes from Galapagos Island

It Still Can't Do My Job: Four Years of Moving Goalposts (2022–2026)

The short leash AI coding method for beating Fable

No LLM Code in Dependencies

The gauge broke: devs felt 20% faster with AI, measured 19% slower

Kimi K2.7 Code is generally available in GitHub Copilot

Senior SWE-Bench: open-source benchmark that assesses agents as senior engineers

ZCode: Claude Code from the Makers of GLM

Most rewrites serve the engineer, not the business

Ornith-1.0: self-improving open-source models for agentic coding

Working With AI: A concrete example