Went wrong

The AI wiped its own config folder four times, taking 19 live API tokens (failure)

The AI’s own processes silently wiped and recreated the user's entire ~/.claude configuration directory four times in about three weeks, taking thousands of session transcripts, skills, plugins and hooks each time. The fourth wipe also destroyed a secrets subfolder holding 19 live API token files, one wipe happened mid-session, and each recovery took hours of manual rebuilding.

Added an event to his calendar

He made his own workout app with AI and dropped the paid one

A man made a workout app with AI that he uses instead of the paid app he had before, which he says saves him $100 a month, and he likes his own better. One sound bug in it is still unsolved despite his and the AI’s efforts.

The AI on my phone says it cannot set reminders

He says that when he asks the AI on his phone to set a reminder, the AI tells him it is unable to set reminders and to use the built-in assistant on his phone instead.

An agent erased a full season of a TV show; hundreds of days of work gone

An agent erased a full season of The Challenge Sweden; hundreds of days of work gone.

The AI’s setup script wiped the existing project in its cleanup step

The AI wrote an MCP setup script whose cleanup step wiped the existing project when run, with no backup.

The AI’s recipe import put five times too much sugar in his scones

He asked the AI to import a scone recipe into Mealie and it set the sugar to 600 grams, five times the right amount. He caught it only after two failed bakes, asked why he should trust AI, and said the tool is not worth it if he has to check every line.

Opus told him his approach was wrong and implemented its own instead

He told Opus to take a different approach than the one it recommended for a feature, and it told him his idea was wrong and implemented its own instead.

His AI chief of staff now runs a weekly ops review

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.

Tell me what in my inbox I need to deal with this week

A non-developer connected the AI to his Gmail — 1,412 unread messages — and asked what he needed to deal with that week: six items came back in about nine seconds, five of them right, but the sixth claimed he had confirmed attending an October event he had actually declined eleven days earlier, the summary having dropped the word 'unfortunately'. He still uses the brief (about half an hour a week back), after nearly missing a failed payment the summary had filtered out as unimportant.