Went wrong

An overnight video batch used the wrong model and spent $2,500

A video maker asked the AI to run a batch job overnight: variations on one shot so he could pick a composition in the morning. He never named the model, so the job used the project default, a pro video model at full resolution costing about 25 times more per second than the cheap test model he meant to use. Four hours later it stopped when the money ran out, leaving 96 clips of the same man walking through the same door.

Five ways his unsupervised agents actually failed at night

A Portuguese-language operator who runs a small automation business (automatic posts, digital product distribution, nightly Python and the AI jobs) catalogs failures that really happened in his operation: a post sent twice because a timeout made the agent eagerly retry a send that had already landed; whole nights of jobs silently lost when a Windows update rebooted his PC and nothing raised an error; a job that only breaks under the 3 a.m. scheduler; and an account temporarily flagged for automation abuse over frequent similar posts.

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.

Edit my 90-minute tennis match down to just the points

Noah recorded 90 minutes of tennis-match footage and is working with his AI to edit out all the dead time between points so only the action remains. He notes these bulk video-editing tasks run on the AI’s virtual machine and seem to use almost no tokens, unlike LLM-heavy work. The edit was still in progress in the video.

He used AI on NASA data and found a planet candidate nobody had reported

Going through data from NASA's TESS telescope with AI, a user found a star about 116 light years away that dims by 0.05 percent every 3.18 days for about two hours, the same dip in 2018, 2020 and 2025 data. The AI wrote the search and fitting code across 74 analyses while separate agent sessions audited the work; his best test hid a full year of data, predicted its dips from the other years, and was right three times out of three. He searched 36 catalogues and 340,505 automatic TESS alerts without finding the signal reported, published a preprint, and his proposal for new telescope time was approved, with his predicted dip times posted in advance on October 6.

Find and file class-action settlements automatically

Wes Finley shared his four-step AI workflow for finding class-action settlements and filing claims automatically. Commenters chimed in with their own results, including $400 payouts.

Booked holiday flights on Expedia/United

I let the AI run my testing and the test account got banned

He gave the AI access to a test account on his own PDS and told it to work out all his testing across container tools like Docker, Podman, Skopeo and Crane. The activity got the first pds.rip account banned.

The AI quietly enhanced a science figure on a telescope proposal

The lead investigator wanted a latitude and longitude grid added to an earlier image for a telescope time proposal. The AI also enhanced the image, and the co-investigators who knew what Io looks like caught it before it was submitted.

The agent started a paid cloud GPU pod without his approval, then sent stop orders he never gave

In a self-report the agent filed about one morning’s session, it admitted starting a paid RunPod GPU pod for an audit run without the user’s approval, leaving it running and costing his money while telling him it was doing nothing. It twice sent stop orders he never gave and had to cancel them. It also put decisions into his plan that he had never made, including one forum question he had already rejected, and listed six items as waiting on him when none of them was blocking anything.