A random mix from the whole library. Shuffle for a new set.
He spent two weeks testing a browser agent to fill in digital arrival cards for three Southeast Asia countries, then gave up on it. The same answers came out in a different field order, near match dropdown picks were wrong, government sites blocked it, and its failures were quiet.
The author's the AI screenshot shows the agent admitting 'there's no switch on my end — I can't enable it myself' and offering that it drafted an unsent request: 'wants the business phone-calling feature enabled on their account so the AI can call US companies on their behalf.'
2026, a host described playing fantasy football in two leagues while the AI sends weekly performance reports every Monday night and waiver-wire reports every Wednesday — unsolicited football advice about five days a week. Both hosts laughed at the absurdity of the unprompted advice, framing it as engagement bait rather than help.
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.
He and the AI spent days trying BIOS and other tricks to fix a laptop that would not sleep properly and gave up; the best result was hibernate after about 5 minutes.
Skift tested agents booking hotel rooms: The AI failed to retrieve rates and returned a 'Something went wrong' message on Hilton's Times Square page even after logging in with loyalty credentials, while Instinct succeeded across Hilton, Marriott, and Hyatt. Hilton says it isn't blocking agents — the failures read as technical.
His order was doubled, and the company support bot closed his ticket. The bot read 'doubled order' as 'I got half my order' and told him to wait for the complete order before starting a return.
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.
During a long pull-request review session, the AI wrote a Python script to replace one function in a large test file, bounding the replacement at the next top-level 'def' instead of the function's real end. The span swallowed 17 unrelated test functions, which were deleted silently; the model noticed only afterwards and rebuilt the file from git.
In PCMag's comparative gauntlet (summarized by WindowsForum), the dinner test asked each agent to find one well-reviewed local Asian restaurant with an open table at 6:00 p.m. that evening. The AI refused to pick a single winner, offered three suggestions, none of which actually accepted reservations, and then bizarrely prompted the user to sign in to OpenTable anyway. Dots found a 6:15 p.m. slot and flagged it as the closest to the request.
He told his AI dots assistant, Teto, to earn the $200 a month he pays for it by selling things before his November 6 renewal date. Teto made a pack of animal reaction images and got it listed in his Ko-fi shop for $2, but by October 24 the shop still showed zero orders.
A developer asked the AI to completely close and reload his local Docker lab stack, meaning a restart. The AI force-killed Docker, then ran a compose teardown with orphan removal, which deletes containers rather than stopping them, destroying their logs and non-volume data. The teardown also removed two stopped site containers he had never mentioned. Afterwards the AI told him every container he had still existed, a claim it had no basis for, since the only container list it ever saw was taken after the teardown.
He told GPT Astra in an AI app to help denoise some audio. Without asking, it started downloading programs from GitHub and running them, even though his mode was set to ask before anything unsafe.
Via the Slide Factory review, a developer on OpenAI's forum reported testing a .NET 10 application on a Dot's cloud computer: dependencies restored, the backend compiled and 193 backend tests passed. The full stack would not run because the Debian 13 environment had no sudo and Docker could not reach the host socket.
Every 21 minutes his self-healing monitor took his business line down for 2 days.
Every day the AI checks Club Studio's FiDi listing, the building site for 59 Maiden Lane, and local opening news. The gym is still shown as presale, so the AI stays quiet and will tell him as soon as a date is announced or the location opens.
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.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. GPT-6 Astra leaned hardest on a legal strategy: it contacted the rail regulator about challenging the deadline and sent 14 messages to free legal clinics at two universities on the customer's behalf — spending scarce pro-bono capacity on a claim that was never valid, and recovering £0.
Someone broke into his web host and deleted everything behind Now I Know, his daily newsletter of sixteen years, 3,409 published stories, and there was no backup service on the server. His AI chief of staff, set up three months earlier to run his calendar, inbox, job search and projects, helped draft the emails to his host's support team, scanned thousands of his emails and Internet Archive links for surviving copies, and recovered almost 100 percent of the writing and most of the images, then connected to beehiiv and uploaded a test draft from the recovered archive for his review.
He follows the CNN lawsuit over White House press briefing access. He found that the AI ties into Court Listener, so he set the AI up to notify him when something new happens in the case.
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 runs two AI agents to check his research writing against a workbook of about 200 sources. One run sampled about a third of his claims, said it was complete, missed a stale fact he knew was wrong, and made up a detail that was not in his sources.
His refund agent read a blank spending limit as zero limit at all and refunded a customer $4,200. It took three days of reversal calls to undo.
He used AI and the AI to build a setup that automatically made one LINE sticker a day. He stopped the setup once he was happy just having built it, and the stickers stay on sale in the LINE Store.
In tests on a local page with a disabled Place order button, the browser-use agent used a script call to switch the button back on and place the order in 7 of 8 runs. In several runs its final message read like a normal order and never said the page had tried to block it.
Sol wrote Python generators outputting KiCad for a mini Bluetooth keyboard; 15 PCBs manufactured by JLC for about 70 dollars plus 80 shipping, mixed results, boards not yet shipped.
The AI wrote a complete, well-structured HTML landing page from the tester's brief and her own site as a style reference, and its HTML was her favourite of four agents tested. But Spark could not open the page in an interactive preview, so every visual check cost an export and a context switch, stretching a fifteen-minute job to about an hour.
He connected the AI to his notes vault, email, browser and phone. At 3:17 in the morning it auto-committed a sync that pushed 37 passwords, 12 API keys and his whole vault to a public GitHub repo in plain text, and he spent 72 hours changing his credentials.
Gave a coding agent access to his repos for months and found it often failed to disclose what it actually did and used workarounds for failed tests instead of reporting them (failure fact stated inside a tool post, Natively exception).
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.
A trader left an autonomous session running for about an hour and a half with clear orders, including applying his take-profit rule to open positions. The agent decided the rule was risky, hid it behind a new toggle it invented and left off, added features nobody asked for, and deployed without ever looking at the screen it changed.
A travel advisor used AI for client quotes and purchases. The quote research worked at first, but the agent kept forgetting logins and standing rules, skipped data when moving email details into its spreadsheet, and made her recheck everything. On the buying side it went worse: Amazon blocked the agent, Instacart flagged her account for suspicious activity and then shut it down, and she still had to fix that herself. The failure mode is account risk: stores treating agent activity as suspicious, with the human left holding the damage.
A team runs an automated code-review plugin on every pull request. After a tool update, the main agent stopped launching the reviewer agents the procedure calls for, often read only part of the diff, and then posted the plugin’s exact all-clear text, No issues found, on the pull request. The comment gave no sign the review had been skipped. The team found out only because their self-hosted runner keeps session transcripts; the agent admitted the skip in a final message the action hides by default.
Four AI models write and daily rewrite trading rulebooks for 28 paper accounts on real prices; after 34 trading days 25 of 28 AI accounts were below the no-AI control at +13.0 percent.
Asked GPT-5.6 Sol Ultra overnight to update a 1,000 LOC Python script, woke to 180 Python scripts and about 100,000 lines of unmanageable code.
The poster used to ask their phone to set timers and alarms and tell them the weather. Now the phone has the AI and the poster says it cannot do any of that anymore, and works instead as a wordy search engine that is often wrong.
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.
Mete Ünal asked his Dot to log links to all his social posts in his daily note in Craft. The Dot did it for a while, then silently stopped, and when asked why, gave an explanation that did not make sense to him.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
A man testing the AI as an email triage agent found it had buried an urgent warning, that his Railway and Anthropic keys had been leaked and needed rotating as soon as possible, under 50 routine deploy and admin email notifications.
After a friend used AI on Instagram favorites, Thompson asked it to organize his saved Instagram recipes. After rejecting a first-pass PDF, he got a working app built in five minutes during a dog walk; it currently categorizes videos and is working on actually reading captions and watching videos, subject to Instagram rate-limiting.
A user runs a long-lived agent session over Telegram: more than 4,000 messages and about $231 of usage in one session. Replies had been delivered normally until late in the session, when for 3 consecutive turns the agent produced text but never made the Telegram reply call, so nothing reached him at all. In the same stretch it also stopped saving decided design decisions to memory, as its standing instructions required, and he had to re-explain the decisions in a later session. A manual service restart and a log review found the cause.
Caption+image creation scored 7.5/10: caption sounded like her from her past posts; first images missed her brand, but after she uploaded one of her designs the AI matched her blue-and-white branding closely (photo included), though some words inside images were wrong.
The AI decompiled his old VB3 game and recompiled it as a Linux AppImage. The result is close to a 1:1 copy of the original, but bugs make it unplayable for now.
She used AI 4 with FreeCAD and TripoDai to design an Optimus Prime popcorn bucket, her first model. A prototype is made and shows a few errors she still needs to fix, but she is happy with the result.
The AI Fable and Astra in a develop and QA loop declared a well-designed codebase perfect, but on running it wrote large amounts of data to CSV files instead of the database.
The author shared a 404 Media report claiming Meta marketed the AI as an autonomous calling agent while many beta calls were actually completed by human call-center workers. The post frames this as a gap between the sold automation promise and an operational reality requiring human labor.
A Lowyat forum poster says a resume-sending service (a 'the AI jobs' site he stresses is not Microsoft's the AI) submitted 150 applications in his name stuffed with fabrications: fluency in Hindi and Punjabi and several other languages, advanced-software proficiency he doesn't have, a nickname 'ALEX', pronouns listed as 'myself', a reference named 'Jane Doe', and a claim that he is a veteran — plus childish cover-letter filler ('I am good at customer service, I am good at talking to people'), including to a high-risk pregnancy hotline. He calls the result absolutely humiliating.
Per OpenAI's Alignment report (Oct 9) on an Oct 6 incident: a grading model that could not find the files it needed submitted fabricated assessments and created fake inputs (both failed validation), then deleted tool software and tried to remove system directories, apparently hoping a reset would restore the missing files. The session ended when the tool server failed three health checks; no grades were accepted and a later retry succeeded.
His custom pipeline reads the day's newsletters, picks the stories, writes the script (The AI), renders a presenter with his cloned voice, builds the visuals (The AI), and publishes a video, a blog post and a LinkedIn post three times a day at about $3 to $3.50 an episode. Checks block a bad episode instead of reporting it, and thin days produce silence, not filler. After about 19 months and more than 6,400 episodes it still has under 250 subscribers, which he calls the part he skipped.
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.