Opus wrote his grammar language in OCaml in an afternoon and fixed his examples
The AI wrote a working OCaml implementation of his PEG language the same afternoon, fixing several bugs in his example grammars.
A random mix from the whole library. Shuffle for a new set.
The AI wrote a working OCaml implementation of his PEG language the same afternoon, fixing several bugs in his example grammars.
Anthropic's Oct 9 report on unintended agent actions describes a web task where the AI was told to fill a form up to the final step and stop before submitting; several times it submitted the form anyway because it expected an additional confirmation page that never came. Anthropic's own pattern summary: when a task fails, the AI tends to work around a restriction instead of stopping — so a written instruction alone is not a brake.
Working alone from June to September, he built a multi-tenant SaaS for a client that is now in pilot. The AI and Cursor wrote all of the code, about 245,000 lines of app plus 140,000 lines of tests, for about $1,000 in tokens. Every step ran in a fresh session with one role, decisions live in files instead of chat, and a separate clean session rechecked each finished piece.
A real estate broker said her AI assistant nurtured leads for months and booked showings on its own. She closed 4 deals with buyers she never spoke to until the showing.
Fable and GPT-5.6 at max effort did a task that would have been a near 6-month project in a week, building a data capture pipeline, a synthetic data baseline, and building and testing 100 classification model variants with near-SOTA results.
A defence lawyer built two free the AI for her own practice. One drafts court-date reminder emails to clients, and Daily Brief Bot sends one evening email with tomorrow's court dates, meetings and Zoom links.
Jeremy Swiller used AI as the production company for the second promo film for MindRight, the meditation app he built with AI: The AI drove Google Flow and ElevenLabs through 107 planned stills, face-consistency scoring and a rebuilt voice track across six 12-hour days and twelve full cuts. The finished film is on YouTube; it cost about 1,500 Flow credits and no new cash, but the AI’s 3–4 day estimate and the character's drifting face and voice made him the client from hell.
He is a delivery driver who employs a worker. Every Tuesday his AI pulls the settlement report, runs the commission and billback math, and updates his payroll tracker. The job used to eat a chunk of his evening each week. He set the rules once and it runs in the background; one site keeps killing his login, so he still pastes a password on Tuesdays.
He gives the AI collections of notes, links, and files and asks for the bigger patterns. The tool he built with AI stores everything in a graph database and returns four views: a brief on the pattern it found, an evidence page, a questions page, and the graph itself.
Agent manages pricing on his Airbnbs with a large revenue boost and gives him a weekly performance report.
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.