An agent ported his renderer to the new graphics API in 24 hours, live
Agent ported his hand-written WebGL renderer to WebGPU, deployed and live in 24 hours versus a 6 to 10 week human estimate.
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.
Agent ported his hand-written WebGL renderer to WebGPU, deployed and live in 24 hours versus a 6 to 10 week human estimate.
He sent the AI a photo of a clock, it worked out what non-standard battery it took and ordered it from Amazon for him.
A researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.
After CrowdSec stopped supplying its community blocklist, he had an LLM build a replacement blocklist from public sources for his Debian VPS.
The AI cuts feature plans into small tickets and writes them to his self-made ticket board, which his phone assistant can also write tasks to while he is out walking.
He is a photographer who found typing alt text for every photo slow going. He built a small agent on his own n8n server: he sends a photo through an Apple shortcut, the agent reads the picture with a local Qwen model, adds the camera data, and saves the finished alt text in an Obsidian note, ten photos at a time.
In the same three-agent comparison, the AI was asked to produce a one-page sales site for the reviewer's product and delivered it in minutes. Presented as a chaptered test ('Test 2: a one-page sales site') in the Oct 17 video.
His son is in half a dozen orchestras and bands, plus cadets and Explorers and Scouts, and his daughter is in reception class at a different school. Both schools send everything by email, the important details are often buried inside one of several PDF and Word attachments, and he kept missing things. Over the years the schools had collected three different email addresses for him, which made it worse. He got the AI to help him build a system that runs on a schedule in GitHub Actions, reads the school emails and drops the events into a shared Google Calendar. It costs him about $2 a month in API credits, which he calls much cheaper than a missed guitar lesson.
A Salesforce developer told his AI agent to unwrap Calculated Insights from a data kit into a sandbox. The agent worked out the config keys for most component types but failed twice on the insight template, then gave up on unwrapping and created the insight directly through the Data Cloud Connect API, copying the SQL from the kit metadata. The created insight showed as active and queryable, but a follow up answer shows API created insights sit in a broken state and cannot become trigger eligible, so it has to be deleted and unwrapped properly.
VC Ian Park posted a Korean-language the AI chat confirming two Prestige-class Korean Air flights (Seoul Incheon–Singapore, Sept 26–29) and a Ritz-Carlton Millenia Singapore twin-room booking with free cancellation to Sept 24. After linking the Google Calendar connector, the AI added 11 Singapore itinerary items (flights, courses, jogging, checkout).
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.