Recompiling a classic SNES game with an agent's help
Recompiling the Lion King SNES game with an agent.
Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
Recompiling the Lion King SNES game with an agent.
GitHub Classroom shut down on August 28, and his Cloud Code Academy ran on it. He wrote a PRD first, then rebuilt the platform with AI over the weekend, with a template repo, feedback pull requests, autograder webhooks and an instructor queue, in 25 commits.
Agent ported a moderately complex workout app from web to native iOS in a couple of evenings, with a test battery.
He is not a programmer, but he used AI to trace a bug through localization files, tech scripts and the game's internal category system. The AI hotfixed a deprecated modifier key in his Clausewitz engine mod, and he shipped a working patch in 30 minutes.
The AI made a new OBS launcher in about a minute that opens OBS and refreshes and checks all of his sources.
He built a household app with AI that holds the family calendar, shopping list, chore rotas, house documents, and push notifications. The family uses it daily, an update in the thread says it survived a move to a new host with its 147 releases intact, and he calls it probably the best thing he has made with AI.
The AI took a 6 month old presentation and updated the branding. He then had to replace images and fix a dozen small things that did not look clearly wrong at first pass. It saved an hour of copy paste work and caused an hour of editing.
Another user describes the AI’s phone work. It called AT&T and argued for a discount because his service is poor where he lives, staying on the phone with real people across multiple transfers and departments for 98 minutes, and got the discount. The amount is not stated. His other two cases from the same comment are recorded separately where they stand on their own.
Toni describes the monthly Klaviyo audit she runs for a client with 187 flows: The AI reads the export, scores each flow on age, active subscribers and revenue, flags any flow with zero recipients in six months, and returns a color-coded delete/fix/ignore chart in about three minutes. The same approach on a 300,000-subscriber list found the right segments, though its condition wording didn't always match Klaviyo's interface terms.
The AI built a complex quiz web app for himself and friends with multiple question types, screen sync, media uploads and scoring, in about a week of evenings (build reported in-window; the comment's complaint about current models left aside).
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.