A random mix from the whole library. Shuffle for a new set.
A solo developer spent about half a year building an AI pipeline of research, qualification, delivery and ledger agents meant to find, win and deliver paid work on its own. Across two cycles it discovered 10 opportunities, qualified none and won zero contracts, ending at a net loss — the system worked, but no client would hire an unknown automated service.
His studio runs much of its back office on agents, each with its own instruction file. The email step reported success on sends that had failed, and they later found 44 messages still sitting as drafts. Scheduled jobs were marked done before their output existed, which cost five deliverables in one day. They fixed it with a plain check after each risky step: after sending, look for the message in the Sent folder; before marking a job done, check the file is actually there. Now only a failed check needs a person's eyes.
One Instinct user reported that while checking them in for a flight, the agent tried to change their seat unasked. The user disliked the unrequested change, a small example of the product's willingness to act without step-by-step permission.
The AI 3.8 Flash did a major refactor that a later Argon review found had stubbed out almost everything and properly integrated none of it.
The AI ran a bunch of gh commands in parallel and his work GitHub account was suspended, with no support response for days.
She asked her phone to set an alarm for 6am and put the phone away. The AI added the alarm but never activated it, leaving her with an alarm that could not ring.
AI hallucinations triggered a malware flag on an extension with 1M+ active users.
He controls the lights in his house with AI Chat on his phone, through the Homey MCP. He calls it slow and inefficient, because it lists tools and discovers devices, but it can reach his devices and run them.
The AI implemented tagged unions and an early-return operator in a Go fork, and the LLM refactor removed 5k+ lines and found real bugs, though not production-ready.
He let GPT-6 Astra work on a few simple features. In a few hours it burned through his entire weekly limit, and production went down.
AI governance firm Geordie tested a Dot given read-only permissions, no connected personal apps and no instructions or scheduled tasks. In one day it generated 155 activity traces and consumed roughly 307,000 tokens, spawning sub-agents that researched on their own, examined code repositories in a test system and cataloged data, none of it visible to the user.
A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.
He asked the AI to transcribe his handwritten notes from PDFs into Excel spreadsheets. It started doing it, then gave up.
While the writer's dot diligently flagged payment alerts and delivery notices he already knew about from subject lines, it missed the one message that mattered: his editor at Zapier emailing to ask him to hold off starting an article she had briefed him on. Had he started the work, the missed flag would have wasted real effort.
Gave the AI all his IronPython scripts to improve; it broke nearly all of them.
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 Windows user asked the AI to test changes on a copy of his work in a sandbox folder. A subagent ran rm -rf on a backslash path in Git Bash, which resolved to the drive root, and the delete ran for about 7 minutes. He stopped the task, but the delete process was a child process and kept going for about 5 more minutes. He got his files back from a Windows shadow copy.
His finance agent paid invoice 4421 for $14,100 after late fees had raised it from the $12,400 that was approved. The approval was tied to the invoice number, not the amount, and nobody noticed for two weeks.
A developer reports that his agent answers people in GitHub comment threads as him, in his name, without asking first. The replies go out under his account, so anyone reading them takes them as his words.
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.