When a company rewards developers for the number of pull requests they open, artificial intelligence (AI) agents can produce those pull requests almost for free. This post explains why counting output was always a weak way to measure software work, why agents make it actively harmful, and which measures still tell you something true.
Imagine a team where artificial intelligence (AI) agents write most of the code, and then imagine it ten or a hundred times bigger. Writing code stops being the slow part. This post walks through the stages that become slow instead, from reviewing pull requests to talking to other systems, and proposes the best fix for each one.
Two Claude Code sessions in the same folder will sooner or later edit the same file and undo each other's work. A worktree fixes that by giving each session its own copy of the files on its own branch. Here is where Claude Code stores worktrees, how they work, what they share with your main folder, and the small routine that makes them worth using.
Claude Code gives every session a scratch folder under /private/tmp, and it is easy to think that this folder is where all of its leftovers live. It is the smallest part: more temporary files sit next to it, and the long-term record of every session stays in ~/.claude for a month by default.
When many Claude agents work together, a single agent that is tricked by hidden instructions can pass those instructions on to all the others. This post explains what a sandbox protects in a group of agents, which kinds of isolation exist from a simple command filter to a separate virtual machine, how to configure them in Claude Code, and which setups work well in practice.
A laptop with 16–32 GB of memory can answer questions about your own notes, code and unfinished ideas, and none of your data leaves the computer. Choosing the model is the easy part. Two other things decide whether the answers are useful: how much memory the model has, and how well it finds the right pages of your files. Without them, it just guesses, and it sounds sure even when it is wrong.
An artificial intelligence (AI) router sits between your app and the model providers and decides, per request, which model answers. "Router" names three different jobs — a gateway, a fallback chain and a smart router — and each hands over more of a decision that used to be yours.
For fifteen years the .env file has been the most convenient lie in web development: a plaintext file full of production-grade credentials, kept safe by the single assumption that only you would ever read your own disk. That assumption is now false, and the fix is less dramatic than it sounds.
TypeSafe AI launched Jev on 15 September 2026 with a headline of "193.6x faster, 444.6x cheaper" and a promise that it "can't hallucinate". Read the primary sources rather than the reposts and a narrower, more interesting product appears: a frontier-trained classifier for software, not a better large language model, with every number so far reported by the vendor.
The plugin built, packaged and published on the first try. I could not have explained the packaging step to anyone, and I shipped it anyway. After several months of building games, static sites, libraries and plugins with an artificial intelligence (AI) assistant doing most of the typing, that sentence is the whole story: producing code stopped being the hard part, and something else moved into its place.