Topic
Agents default to 'make it configurable' because training data rewards flexibility. Every flag they add is a branch nobody tests and a decision nobody made. The cheap counter-move is to force a default first.
Read articleBruno solved the cloud-lock-in problem. It didn't solve the drift problem — and once an AI agent starts treating your request collection as truth, that drift stops being annoying and starts being expensive.
Read articleThe agent finished fast and the PR looked clean. Then package.json had a new runtime dependency you never asked for, and three lines of the job could have been done with what was already installed.
Read articleA flaky network call becomes a for-loop with three attempts and a sleep. CI goes green. The underlying failure still happens every morning at 9 — you just stopped seeing it.
Read articleYou asked for one endpoint. The diff has the endpoint, a renamed variable across fourteen files, a rewritten error helper, and a formatting pass. You can't tell which hunk is the feature and which is a side quest. Here's the habit that fixed it.
Read articleAn agent reads your file, writes a summary for the next session, and in that paraphrase the generic constraint, the discriminated union, the branded ID all collapse into a vague noun. The next session then builds on a version of your code that never existed.
Read articleThe working tree after a failed agent loop is its own archaeological dig — five stashes, three branches, a commit message that says 'wip', and no record of which attempt actually worked.
Read articleAn agent that runs tests locally and reports green is telling the truth — but only on its machine, where the .env, the local DB, and the cached node_modules exist. CI runs a clean checkout. The gap shows up in your pipeline.
Read articleYou hand the agent a map of the codebase. By the time it acts on it, the map is wrong. The fix isn't a bigger context window — it's cheap freshness checks.
Read articleWhen you ask an AI agent to add tests, it writes tests that pass on the first run. That's the problem. The sanity check is cheaper than you think: delete the implementation and see which tests still go green.
Read articleAn agent that says 'done' after starting a dev server, a watcher, or a docker compose stack often leaves those processes running in the background. By the next task, your machine is a graveyard of half-finished services.
Read articlePasting just the stack-trace line into an AI coding agent rarely fixes the bug. The agent fixes the line you showed it, not the input that produced it. The evidence that matters is almost never in the error text.
Read article