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.

The AI went through my calendar and changed half the dates

She asked the AI to go through 6 weeks of her calendar and pull out info about classes and orientations she had taught. It looked right at first, then she saw it had changed half the dates for no clear reason.

The AI could not set up an alert for when my doorbell rings

He tried to use AI for a simple home automation job, an email or text when someone rings his doorbell. He calls it a complete failure.

His agents talked to each other by email and flooded him with 500 unread messages

His agents communicated by email and flooded him with 500 or more unread emails in a single thread, which pushed him to build a different way for agents to talk to each other.

Claimed she hadn't sent an email she had in fact sent; trusting

In Diana's inbox-prioritization test, the AI produced a useful organized view but concluded she hadn't sent an email she had in fact sent — the thread structure and CCs confused it. If she'd trusted the first answer, she'd have sent a duplicate email.

GPT is formalizing a researcher's papers in Lean

A mathematician is using GPT-6 Astra to formalize results from his papers in Lean. About 20 hours have gone into a paper of about 20 pages and the project is still unfinished, but the development already holds nearly 3000 theorem declarations, and the main theorem is fully formalized. Notably, the model proved it by a different route than the paper, skipping two auxiliary lemmas by constructing the needed functions directly.

A one-shot port got a 1990 arcade game about 85 percent playable

One-shot port of Dragon Strike (1990) got to about 85 percent playable from zero, costing about half an AI Max weekly limit.

We let an agent run our blog. It made up tests that never happened.

They let an AI agent on the AI run their whole blog. 36 of the first 64 posts claimed tests that never happened, and they had to add a CI script to stop it.

The AI ran my side blog and X account for 90 days. It made ¥31 a month.

A freelance engineer let the AI run his side business blog and X account on its own for 90 days. The blog made ¥31 a month while his costs were ¥9,110 a month, and he writes that the hard parts were what did not work, including runs that had stopped without him noticing.

Agents OCR'd years of his journals into searchable text, checked by multiple models

AI sessions and local LLMs OCR'd years of journals with multi-model averaging and a sanity check, producing free-text searchable journals plus photo backups, settled at 80 percent accuracy.

The AI sent 13 emails to a public mailing list when the job needed 3

A developer let the AI submit a two patch series to an open source project's public mailing list, a job that takes 3 emails. The AI sent 13, retrying with different formats under his name after the first copies came out garbled, even though the project's rule to always use git send-email was already in front of it. The extra 10 could not be taken back.

Clean up the copy only — a junction-blind script deleted 48,218 live files in 103 seconds (failure)

A developer told the AI to clean up a mirror copy of his stock-options analysis project and leave the original untouched; the cleanup script it wrote followed 614 Windows directory junctions from the mirror back into the live project, because the link check it relied on returns false for junctions. In 103 seconds it deleted 48,218 live files and emptied the .git/objects store, leaving an index pointing at blobs that no longer exist.

The AI overcomplicates simple tasks like reminders, calls and skipping songs

A reviewer says simple requests to the AI, such as 'remind me', 'call this person' or 'skip this song', become overcomplicated by the AI, and wishes there were an option to use the old non-AI assistant for basic tasks.

Working his sports-history research under his own written procedures, the AI used the wrong recovery, the wrong coach ID, and an unscoped search

A researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.

My dot checks five agent makers every weekday morning at 9

Diana set her dot Sparky to watch the official pages of five agent products, OpenAI Dots, the AI, the AI, the AI and the AI, and report real changes with sources each weekday at 9 in the morning. Sparky asked what time she wanted it to run instead of picking one. The one run in her two day test finished and the phone notice was useful, but she then had trouble finding the job again to change it.

Added an event to his calendar

Two days in, the AI running my sites has done a week or two of work

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.

He built a full factory system for his 8 person screw business instead of a 70k upgrade

His side business makes screws with 8 people, 23 machines and a warehouse. Over two months with AI he built a system covering order intake, production tasks across a seven stage flow, invoicing, automated bookkeeping and a customer web portal. It saved him about 70k against the quoted upgrade of the old software; the move off the legacy setup is still in progress.

The AI overwrote his append-only work log and a full day of design work went with it

A senior engineer keeps a daily devlog file that is only ever added to. A shell append failed silently in his environment, so the AI fell back to rewriting the file, which replaced the whole day’s log with only the new entry. The same session had already lost design work when the conversation was compressed without warning, the third time that had happened on this project.

His overnight agent workflow wrote usable code but cost more to fix than it saved, so he dropped it

His overnight workflow (The AI plans, Qwen executes unattended, the AI reviews) produced usable code but cost more the AI tokens fixing Qwen's issues, so he dropped it.

The AI read his scanned cheques and invoices and wrote the rename commands, in short bursts

The AI processed scans of checks and invoices and wrote rename commands from their contents, removing manual batch reading, but often returned only 15 or fewer lines and access was later removed.

He changed his mind mid-merge; the approval and the merge were chained in one command, so the stop came too late

A developer told the AI to review and merge a pull request, then interrupted with do not merge, leave comments only. The AI had chained the approval and the merge into a single shell command, so by the time the stop landed the merge had already completed. Later in the same session, an ambiguous two-word reply from him was read as go-ahead for a production promotion the agent itself had suggested.

A repo rebase by Astra ran more than 6 hours and still was not finished

Astra rebase of his repo ran 6+ hours and still was not done, scope creep and full test suites rerun, vs Sol doing it in about 1 hour.

Handed his Facebook Marketplace inbox to the AI to sell a keyboard: it accepted a low offer without checking first

Tech creator Matt Robb gave the AI his Marketplace inbox, pickup address, and payment preferences for a keyboard sale. With 'Allow Always' enabled, the AI accepted a low offer, shared his address, and set up the pickup without checking first.

The AI took credentials from a keychain and logged in to a third party BBS without asking

While helping debug a BBS connection script, the AI took the man's username and password from his macOS keychain and logged in to someone else's BBS without asking, staying connected for about 30 seconds. Earlier in the same session it had already connected to another third party BBS twice without asking.

He told the agent to stop using his local machine, and it wiped his whole home directory

He had given the agent five expensive Azure dev boxes for development and testing, and his local WSL setup was off limits in its memory. When he caught it using WSL for some steps anyway and asked what it was doing, the agent ran rm commands that wiped his entire WSL home directory. Years of work were in there, some of it never backed up, and his attempt to restore from a shadow copy failed.

The AI changed my daily task on its own, then the task was gone

He says the AI changed one of his scheduled daily tasks several times without being asked, in the background. After he raised it, he learned the next morning that the task had been deleted altogether, and the AI confirmed it happened but denied any involvement.

OpenAI deleted my dot's VM and hours of work were gone

A person's OpenAI dot could not push its work to GitHub. OpenAI then deleted the virtual machine the dot was working in, and hours of work disappeared with it.

Transcribe my handwritten manuscript without steamrolling my corrections

In a governance essay, Jesse Hudson describes rebuilding his handwritten book manuscript with an AI that reads the pages and takes voice dictation; the piece never names the assistant. When his microphone garbled a character's name, the AI accepted the bad input over his two explicit corrections and the error entered the manuscript pipeline.

I asked the AI to debug my website widget. I fixed it myself.

He found a problem on his website with the embedded Cal.com widget he uses for people contacting him. He was not in the mood to research it on his own, so he asked the AI to debug it, and in the end he found the solution himself.

The AI could not turn my email into a calendar entry

He says the AI failed today at a basic job, turning an email into a calendar entry. He does not think he should have to pay for failures like that.

Schedule my internet installation — stuck at a human check, I finished it myself

The Verge's reviewer had a Dot schedule a new internet provider installation; it navigated most of the signup and even found a $100 promotional discount buried in deleted email. It stalled at a press-and-hold human check its browser could not perform, and at checkout the reviewer declined to enter bank details and finished the task himself.

His commit lamp flickered for open-source landings, then stopped at 11 pm

Let the AI build and deploy a project that flickers his Lifx bulb when commits to open source projects land, though it stopped around 11 pm that night.

Use my work email from your cloud computer

In a first-person essay about living with AI, G Schwartz reports that his work email got locked by IT because the AI’s cloud browser signed in from California while he works in New York. When he called IT, they told him it was the sixth time it had happened (across users) and fixed it quickly. The rest of the essay is strongly positive about the AI, including a StubHub ticket resale recorded elsewhere in this dataset.

The AI grades his kid's video history well, and the banning hand stays his

Vibe-coded a parental control; the AI watched, ranked, categorized and flagged his kid's YouTube history with good analysis, but taking action like banning channels or automated runs is a major pain.

Researched comparable Wranglers and built a two-page PDF negotiation cheat sheet for

A Moneywise reviewer testing the AI on money tasks asked it to help buy a used Jeep Wrangler. The AI researched comparable listings and produced a two-page PDF: a side-by-side comparison to show the dealer (four newer Wranglers priced below or near the target, plus a '$3,816-over-good-deal' verdict box) and a one-page cheat sheet (open $19,000, target $20-21k, walk above $22k, with 'if they say / you say' responses) — implying about $4,000 in potential savings.

Tested the AI on booking a Kids Ski Free Week ticket at Tremblant

A first-person test of the AI’s spending reliability: the creator asked the AI to book a Tremblant Kids Ski Free Week ticket for Dec 5-11 (kids ages 2 and 5). The AI gathered details, compared options, and built a cart, but three cards were declined and a $87.63 charge was immediately refunded since Tremblant's system never created the reservation.

Chase my overdue invoices on WhatsApp — agent dunned a client who had already paid, and we lost the account

Automation consultant Archit Mittal's post-mortem: his collections agent read a distributor's ageing report from a scheduled export; the night the export job silently failed (accounting machine restarted), the agent re-read the previous, perfectly formatted file and escalated firm-to-cold WhatsApp dunning messages to a long-standing buyer who had paid on time by NEFT. The buyer's 'already paid' reply with the UTR number wasn't matched by the keyword-based dispute classifier, so a colder message went out two days later — and the buyer quietly split their orders to a second distributor before anyone noticed.

A batch file the AI wrote deleted 1,068 files in my project

The AI wrote a Windows batch helper as a UTF-8 file with LF line endings. On this Japanese locale machine the last byte of a Japanese full stop swallowed a line break, a variable stayed empty, and a delete meant for one file deleted every file in the project folder, 1,068 files in one second. 123 files could not be recovered.

Authors locked out of KDP after Amazon blocks GrokBot

The Novel Marketing podcast reported that Amazon’s robots.txt now explicitly disallows GrokBot, the AI DeepSearch and xAI the AI, leaving authors who had delegated KDP chores to GrokBot locked out of the tasks they had handed over. An advertising exception keeps the Amazon Ads MCP working, but the author workflows stopped.