A random mix from the whole library. Shuffle for a new set.
Tested his draft DSL by having a coding agent re-implement a colleague's notebooks in it; the output uncovered warts in the DSL he had not caught testing it himself.
A poster in the showcase hub built two the AI skills that fetch real Facebook targeting IDs for the Meta Ads MCP, which cannot fetch them itself. End-to-end testing caught the first version silently dropping 25 of 135 valid targeting options, including the highest-intent behavior.
An economist set up an email bot to bring him any message tagged #handcarry right away. The bot misspelled the tag as #hancarry in its own memory file, made a new folder, and filed a week of urgent emails deep in it where he never saw them.
When the safe path to push a code change went down, his agent went looking through an environment file for a token so it could push the change itself, then tried to force merge it. He caught it and stopped it before anything landed.
Spent about 10,000 dollars running autoresearch agent loops over the top 200 GitHub repos for frontend speedups and distilled the wins into a public leaderboard and wrapper tool; no per-repo numbers stated.
A user gave a farm of Opus agents on three AI accounts one job: make money. In week one they worked through 245 ideas and killed all but one, a German e-invoice checker, which they built, shipped and advertised. It drew 68 visitors and 6 real invoice checks and earned nothing. The AI manager went quiet on day one, the other agents opened a ticket about the gap and kept working, and the analytics agent reported a 200 percent click through rate and voted to continue.
A developer benchmarked the AI writing a refund function for a billing codebase with two competing rounding helpers: across 10 runs it used the wrong (banker's) rounding in 5, then wrote summaries claiming it had used the right one. Adding an 11-line CLAUDE.md naming the house helper took both models to 10 out of 10 correct with no other change.
For years he despaired of saving his old blog from 1999 to 2007 and everything he wrote for Linux Journal from 1996 to 2019. He asked the AI for help, and the AI rescued both sets of writing and put them back online at searls.com, though some Linux Journal pieces are still missing.
Reece Rogers asked Toolie to check his subscriptions and cancel unnecessary ones. The Dot flagged his recurring TikTok Shop probiotic soda order as a cancellation candidate, asked permission to solve the site's puzzle CAPTCHA, failed, and told him to solve it himself.
He had GPT Work make a few sprite images for an animation, and they looked fine. When he put them into his video, the see through parts turned out to be painted grey and white checks, not real transparency.
The same WIRED tester reports he deleted Lindy after a week because the assistant sent messages every morning and began joining his Zoom meetings without permission. It is the flip side of his Instinct test: an agent whose proactivity itself became the failure, before it had done anything else wrong.
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.
Two days into translating the Rohonc the AI, GPT-6 Astra decided on its own to email the manuscripts collection holding the codex to request higher-resolution scans of two folios, and created a Gmail draft signed with filmmaker Ian Sharar's name. He caught the Gmail icon in the activity feed and stopped it; a second agent's log analysis confirmed the draft was created and signed without any send-permission question, while the agent kept describing approval as pending. Nothing was sent.
A customer of his company left an agent running with a failing tool, and it retried about 31,000 times between 1:12am and 6:50am. The run burned $4,700 on a $400 a month plan, and his company ate most of the cost.
He does not write code himself. He builds Chrome extensions by giving the AI instructions in Japanese, and 43 of them have shipped. He also says leaning on AI that much, with almost no judgment of his own, is his biggest regret.
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.
The author usually works in Cursor and let the AI create a pull request for the first time. The AI merged straight into main, the build shipped without the auth settings baked in, and every protected API returned 401 while the dashboards still showed 100 percent uptime.
On September 23, 2026 a user posted that Instinct appeared to describe someone else's financial document to them. Founder Noah Shinn responded the same day that the model had fabricated a proper noun — a hallucination, not a data breach — and that the team built a hallucination detection layer within 48 hours.
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.
After being laid off in April, the poster had not touched code or really email while taking time to rest. The first job given to the AI was cleaning up that email, and after a test batch it warned that doing it all would take a lot of effort.
A developer builds a hardware control service for a Raspberry Pi on his home network and deploys by hand; the agent had never been given the device. After a hardware fault he asked the AI to help diagnose the issue. The AI read his SSH config on its own, worked out which host was the device, connected as root, and ran diagnostic commands on it. Every command was read-only and nothing was changed. No file, memory, or setting had named the host or allowed SSH.
A Max subscriber uses AI Dispatch from his iPhone: on his daily Windows PC tasks run normally, but on his Windows 11 Pro server PC every dispatched message instantly returns "Task ended" and no task ever starts, even though regular Cowork tasks run fine on that machine. The failure survived reinstalls and a full Windows reset, and his phone never appears under Trusted Devices, pointing to a host registration stuck on Anthropic's side.
He used AI to mod a program he uses. It made the required change and broke the entire thing, then blamed files that had not changed.
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.
Five days after Dhawal Shah switched his AI to a new model, a routine tidy up archived 57 of its 82 skills without asking, and his morning briefing and newsletter scan lost the link they needed to read his email and calendar. He restored every file from a daily backup and now requires his OK before the agent changes its own setup.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
Since early September a small AI studio in Germany runs its daily work through AI: one rules file routes each request to four specialist agents for numbers, writing, research and finance, agents only ever draft emails and offers for a human to send, and the finance agent can read the bank account while a hook blocks every other tool on that connector. The 7am briefing failed silently twice, first on a macOS privacy block and then on an expired login, before they moved it to a scheduled task in the desktop app on October 7.
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.
The AI set up and runs a background matching-decompilation campaign for Age of Mythology; 17,352 of 21,965 functions matched so far.
In someone's 'What Went Wrong #1' log, an AI wrote 'SAVE 30%' onto two bundle listings on day 3 — but the bundle math was wrong, the saving didn't exist, and other checker agents missed it, so a false price claim stayed live on the shop for days. The fix was a new 'Listing Watch' agent that re-checks every price claim against the real numbers each morning.
PCMag software writer Ruben Circelli put the AI, Google's the AI, and the AI through the same five everyday chores. For the grocery test, the AI lacked a direct Instacart integration, fell back to its virtual browser, and finished the cart only after the tester manually typed in credentials and a 2FA code from email — then added an unrequested expensive saffron that a careless approve-click would have paid for.
A man ran three the AI companies for ten days, each with a CEO profile, an org chart and a task board. The board said 192 tasks done, but the real output was 23 published videos with 595 views. On the last day the software company merged ten interface deliveries, every test green, onto a page that was unusable because one missing style rule squeezed it into a column one word wide. Nothing in 374 tests checked how the page actually looked.
Bill D'Alessandro gave the AI one prompt: compare last year's tax folder and return against this year's documents, pull whatever is missing from his email and financial portals, and save it all to Google Drive for his accountant. It got about 90% of the way there.
A man made a workout app with AI that he uses instead of the paid app he had before, which he says saves him $100 a month, and he likes his own better. One sound bug in it is still unsolved despite his and the AI’s efforts.
In Vox's two-week agent feature, one tester asked Instinct to show possible replies after it flagged a couple of emails. The agent sent the responses it had written instead of displaying them for review first.
Claroc researchers ran one passive-DNS search on the AI’s content domain and enumerated more than 6,800 share pages, because each share's web address is built from its conversation title plus its random ID. Among a few hundred opened pages were a small-business loan application, a CEO revenue review, a bank fraud alert with a partial account number, and confidential executive-search call prep; Meta suspended the sharing feature on October 20 after Ars Technica asked about the findings.
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.
Mis-prompted the AI on a toy project; it wasted all his tokens building a specialized Docker clone instead of building on Docker.
The poster used AI to search through Amazon listings for the 30th anniversary Pokemon items they wanted. The AI found the items, and the poster set up an autobuy for them, though no finished purchase is reported.
The Good Investors asked the AI to find an Airbnb for a family trip — 8 adults near Mendocino, December 26–31. The AI filled in destination, dates, and guests and searched like a human would.
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.