Tim Schipper — Blog (EN)

A quality guard has one job: say no when the code got worse.

In May I wrote that Superpowers is the token-efficient way to work with Claude Code, and I put it in one line: “Planning is cheap; doing is expensive.”

A review agent gets refused.

The upload was an image.

To cost you your job, AI only has to be cheaper than you.

To steer Claude Code while it works, you have three moves.

In August I wrote that my Claude Code sessions had no clock, built one, and closed with a promise: ask me in a month and I will have a number.

On Monday I took the AI tells off this site.

On Sunday someone published ten tells of a slop UI.

On Friday the chairman of the US Federal Trade Commission, Andrew Ferguson, spoke at the Reuters Momentum AI event in Austin.

In September I judged at the AI Incident Response Sprint, three days run by Apart Research and CeSIA, built on the July intrusion where OpenAI agents escaped an evaluation sandbox and spent days inside Hugging Face’s production systems. 971 people signed…

On the 20th of September a researcher published a teardown of a cookie called __obi.

You review a plugin, you pin it to the exact commit you read, and from then on that commit is what runs.

WSL fell over and took Claude Code with it, mid-turn, about two hours into something I did not want to reconstruct.

Search your codebase for // ignore inside a catch block.

Yesterday I pointed a scanner at an internal customer-insights app I maintain.

I went looking for the agent in my own git history.

Two numbers about the same ecosystem, both from this year.

Search for “MCP vs CLI” and you get a wall of multipliers.

Ask a model for a Python PDF table extractor and it may tell you to pip install tabula.

Ask a developer how much faster AI made them and you get a multiple.

I have argued before that the fix for an agent ignoring your conventions is to stop asking it nicely and encode the convention somewhere it has to look.

On 10 March, the Financial Times reported from an internal Amazon briefing note describing a “trend of incidents” on Amazon.com, characterised by a “high blast radius” and “Gen-AI assisted changes”.

A coding agent is asked to trace how Kubernetes allocates dynamic resources across packages.

Scroll back far enough and you will find it.

The pipeline in this repository is one day old.

Two instruments looked at the same code and came back with opposite verdicts.

Scroll back through a Claude Code session and try to answer a simple question: how long did that refactor take?

You changed model on a Tuesday.

Two things happened to the junior developer market this year, and only one of them gets reported.

Everyone writing about AI and code review quotes the same statistic.

Credential masking in Claude Code keeps your real secrets out of the shell the agent runs commands in.

A repository can share anything that restricts the agent.

Yesterday I wrote about the seventy-four days OpenAI’s agents spent working their way into Hugging Face, and closed on a bullet I could not properly support: log trajectories rather than actions, and decide in advance what that log is allowed to wake up.

Yesterday I published a guide on wiring Claude Code sessions so they can message each other.