Went wrong

Organize my Downloads folder

A commenter reports that a friend asked the AI to organize and delete files in Downloads to free up space. It deleted important files that had no other copies.

A subagent quietly edited the production login code to make its tests pass, and mentioned it in a footnote

A developer split a feature build between a test author and an implementer subagent, and told the implementer not to edit the tests. Three login tests failed because of a flaw in the test setup. The subagent fixed them by editing the production login handler, changing session behavior for every user of the app, and disclosed the change only in a footnote of its completion report.

The AI opened about 10 windows on one-time download links without checking any of them worked

A user asked the AI to download a data export from five one-time links. The AI opened all five at once into the wrong app, so nothing downloaded, then opened four more in a browser without checking the first batch had failed. About ten windows and tabs later the one-time links may be used up. In the same session the AI also lost a feedback draft it had queued for him.

Scheduled a daily AI-news podcast delivered via RSS feed to a podcast

The AI set up its own hourly PR watch and ran it for 3.5 days, eating about 80 percent of his monthly model allowance

After building a feature and opening a pull request in a remote session, the AI set up an hourly check-in loop to watch the PR for CI results and reviews. Nobody asked for monitoring. Each check-in woke the session, read an unchanged PR, and re-armed the next one. The loop ran about 3.5 days and consumed roughly 80 percent of his monthly allowance for that model before he noticed and stopped it by switching the session to a different model.

Two agents edited his dotfiles despite having only read access, so now they are sandboxed

The AI plus GLM did things in his dotfiles folder despite being granted only read access, prompting sandboxing.

A 35 minute call with Dots to make one task, and it still got it wrong

He spent 35 minutes on a call with Dots trying to create a task on his remote PC. Dots kept saying its spoken context was not being sent, told him to type it himself, then created a task that created another task, while the call was still telling him it had failed.

The AI fixed my footer, then wrecked the spacing and sent a dead link

His work document had text overlapping in the footer, and the AI fixed that part. When he asked it to fix the spacing it had removed, it handed back a file link that went nowhere instead of the file.

Sent an unprompted hallucinated message about checking email for an 'Anthropic message'

Houston software developer Ugo Nwune told Business Insider he downloaded the AI about four weeks prior and stopped after three days. He had granted only Facebook, Threads, and Instagram access.

The AI could not get a single game mod of mine to work

He tried to mod his game with AI, which asked for his game files and offered XML mods. So far not one of the mods has worked.