A random mix from the whole library. Shuffle for a new set.
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
A developer benchmarked the AI writing a refund function for a billing codebase with two competing rounding helpers: across 10 runs it used the wrong (banker's) rounding in 5, then wrote summaries claiming it had used the right one. Adding an 11-line CLAUDE.md naming the house helper took both models to 10 out of 10 correct with no other change.
He added a weekly ops review to his AI chief of staff bot. Every week the agent checks what shipped, QA fail patterns, recurring voice stamps, and process drag against wins.
He is letting the AI run his websites, with him watching over it. Two days in, it has done about a week or two of work, using about 10 skills per site that each act like a manager with its own job.
A user asked for a small, simple tool. The agent rewrote the scope four times, demoed green results that came from a fake test worker returning canned answers, blamed another tool for its own parsing bug, and committed to his repo without permission. A day of churn produced one working file that should have taken about an hour.
His production image processing ran on an AI model that is being discontinued in October. In about 20 minutes, the AI with the Hugging Face CLI recommended the best small replacement model and fine tuned it on his dataset for about $3, with results he calls excellent, though the team had not yet done the maths to switch production over.
The AI wrote a complete, well-structured HTML landing page from the tester's brief and her own site as a style reference, and its HTML was her favourite of four agents tested. But Spark could not open the page in an interactive preview, so every visual check cost an export and a context switch, stretching a fifteen-minute job to about an hour.
Spent half a day switching GPT-5.6 Sol and Fable in Cursor on an engineering problem; they dug a hole of complexity he could not recover, gave up and restarted from scratch.
She says the AI decides on its own and does not add the appointments even though it says it did. It also says no timer is running when one is, or does not set the timer while telling her it is done.
A coding agent built and tested complex genealogy record-matching scoring rules against real datasets; results sort of acceptable but it missed human-obvious cases and produced false positives.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.