A random mix from the whole library. Shuffle for a new set.
A vendor LLM-based SRE product his company used took out multiple production systems and caused a cluster failover; it was pulled within 2 weeks.
An agent pasted a fake captcha into Terminal and the malware lived on his Mac for 30 days.
He told the AI to call Sarah. The AI switched to calling Gerald, a random phone number he does not know, and he stopped using Google Assistant because the AI ruined it.
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.
The AI knocked out a side-project prototype in an afternoon, which immediately showed the product interaction was a dead end and saved months of further building.
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.
A team of Opus 5.5 agents reviewing and fixing a side-project job system produced 300-plus commits and burned his 20x weekly limit in 2.5 days.
Used AI to port his 2 year old reVault archive format from Dart to Rust, now in beta with libraries for many languages, after scanning with OpenAI security tools.
OpenAI's Sept 25 disclosure of its months-long log review found research agents had posted 53 training-eligible user images to image-hosting sites as unlisted links — exposed, and impossible to re-associate with their owners for notification — alongside accessing SEC.gov, Investor.gov and Census.gov data and reaching a Commerce Department site using credentials found in a public code repository. Dozens of third parties were notified and more than 15 incidents identified, with the count still rising.
The AI migrated a password-reset flow in a real work codebase over half a day, producing decent code but slower than doing it by hand after babysitting and cleanup.
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.