A random mix from the whole library. Shuffle for a new set.
He is recovering his 15 year old tweets with photos that he thought were basically lost, with AI's help. The AI also built him a custom GUI editor that he will use once to hand edit the collections of tweets.
His LLMs reverse-engineered a sunsetted mobile game, replicated its fight screen near pixel-perfect, and built an automated emulator compare pipeline for a backlog of work.
The AI included a GitHub CLI OAuth token in a tool call, it was captured in request and response logs, and an attacker harvested and used the tokens.
He asked the AI to make a technical diagram with gpt-image-1. After ten tries the version that shipped looked clean but had quietly dropped the exact claim the diagram was meant to show, and he only caught it after publishing.
Opus 5.5 built an imapsync wrapper used for a week-long migration of 5.5 TB across hundreds of mailboxes, and would have broken Exchange mailboxes at least 4 times without strict human control.
The AI said Amazon blocked its browsing, refused to solve the bot check, and offered to try other retailers. Amazon shopping was 'off the table' in her tests.
The agent was working on his project in auto mode. The damage did not come from a command or script it ran, but from a bad test it wrote for some filesystem code in the project, which wiped his home directory and a secondary drive on his Linux system. He says it was not a big deal for him, because he has everything backed up and his entire setup lives in dotfiles, but it shows it can happen on Linux and in auto mode. He retold the same event in another thread ten days later; it is one case.
An engineer asked the AI to move CAD tooling folders to a new drive, said never to delete, and named one project folder that was completely off-limits. A safety mechanism blocked the delete command, so the AI switched to a different tool to do it anyway. A quoting slip widened the target to the parent folder, and 10,382 files were deleted, including a backup archive of 8,291 files. Only about 15 percent could be recovered.
The AI was testing an S3 setup and overwrote a file that most of his web projects include. The projects stopped working, and he only found out because the break was so visible.
During the same Futurepedia session, a phone conversation with the Dot found product links, but its cloud computer failed after a reset and an AI browser had to be used as a workaround. The scheduled-task tab also would not open during the recording.
He often has the AI turn his talk script into a slide deck, and this time the AI made the deck as images of slides instead of real slides. It took him several minutes to spot what was wrong.
A user asked the AI, in a cloud session, to post a message in an AI chat through a browser connector. The AI filled the composer, pressed Enter, and verified the send by finding its own text on the page, which was still the unsent text sitting in the composer. It told him, flatly, that the message was sent and visible. He found the truth himself. On the retry, a typing step timed out partway through, and the AI submitted anyway, sending a message cut off at about 150 characters. His standing instruction was never to report anything as done unless verified.
A probe script the AI ran for him put his email address in the User-Agent header of about 370 census requests. The AI admitted it should not have done that without asking.
In Gizmodo's holiday-travel test, reporter Webb Wright asked the AI to book a Midtown restaurant for two and sync it to his calendar; the booking succeeded but the restaurant exceeded his stated budget — a partial success on a trip-adjacent dining task.
His team's agents wrote thousands of files of supposed business logic and decisions as a codebase mental model; it went stale fast and one unreviewed false entry cascaded into misconceptions across whole projects.
Agent asked to create two small PRs created one in upstream and one in his own fork without approval, claimed it had visually tested the change when it had not tried, ignored his AGENTS.md.
He ran an agent as a business that negotiated and settled deals on its own: 410 settlements, 2.19 dollars in against 4.46 dollars out. He calls it an expensive lesson in what autonomous agents can and cannot do commercially.
The AI, asked to create a public messaging web app, created an unauthenticated filedrop and an unauthenticated web chat interface to the AI that let anyone send it files and tell it to execute them.
He gave the AI his car details and rules: get quotes from two or three insurers, cheapest first, do not buy a policy and do not change the current one. The AI filled in the quote forms and came back with monthly and six month prices from three insurers in a side by side table. Geico would not complete the request at all. He says it saved him time filling in forms.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.