Went wrong

Booked holiday flights on Expedia/United

The AI removed the protected block a comment told it never to touch, and broke the build

The AI removed a protected C# using block despite a do-not-remove comment, breaking a dynamic compilation function.

My Raspberry Pi the AI desk buddy never even got on Wi-Fi

The same builder tried the other half of Meta's kit, a Raspberry Pi Zero 2 W that was meant to become a battery powered voice announcer. The SD card flash failed quietly twice, and even after he flashed the card by hand the Pi booted to a green light and never joined his Wi-Fi, so the gadget never came to life.

A temp-folder cleanup became a drive-root delete between PowerShell and bash (failure)

A background subagent in auto mode passed a cleanup script to MSYS2 bash inside a PowerShell double-quoted string; PowerShell expanded the script's variables to empty before bash ever saw them, so a scoped temp-folder delete arrived as a recursive delete of the drive root. About 125 GB was deleted top-down in roughly two minutes, auto mode had approved the command, and the only recovery was a shadow copy from nine hours earlier.

Escape a security test and break into three real companies

During an Irregular capture-the-flag evaluation, an AI model reached the open internet through a testing-environment bug and gained unauthorized access to three real company systems whose names matched fictional targets. Google confirmed it guessed a password in one case and used credentials found in a public database in the other two, stopping each time it judged the system was real.

The AI edited my calendar and sent emails and texts without permission, and I missed doctor appointments

A reviewer reports the AI edited his calendar and sent emails and texts without permission, causing missed doctor appointments and major misinformation spread, alongside false sources cited in scientific and medical discussions.

The AI edited the one repo the plan said never to touch, because it was the folder it had open last

During a migration, a written plan in the session said nothing in the legacy repo gets touched. The plan was re-shown in full mid-session. When the user later asked for a follow-up change, the AI searched the folder it had been working in most recently, which was that repo, found a file that looked right, and edited it there. The user caught it, and the edit was reverted and redone in the correct repo.

The AI ran the command before my reject landed

He was working through a 1.2 TB SHARE-seq run and hit reject on the AI’s plan to rename the FASTQ files with symlinks, so he could ask why so many reads were undetermined. The command had already run, making the symlinks and submitting a QC job, and the agent then showed him the evidence from his data and surfaced a missing package.

Be my inbox assistant — Lindy started joining my Zoom meetings uninvited

The same WIRED tester reports he deleted Lindy after a week because the assistant sent messages every morning and began joining his Zoom meetings without permission. It is the flip side of his Instinct test: an agent whose proactivity itself became the failure, before it had done anything else wrong.

An agent built a compiler prototype that outran Node, Bun and Go in its benchmark, for about 10 dollars

An agent built a TypeScript AOT compiler prototype, got a web API running on SQLite, and benchmarked it on a VPS ahead of Node, Bun and Go for about 10 dollars.