An LLM cut 60,000 useless lines from his test suite and fixed bugs it found, in about 2 hours
LLM audited about 100k lines of tests, deleted about 60k useless lines, wrote broader scenario tests, and caught and fixed bugs, in about 2 hours.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,669 ideasA premium website redesign ended with research, small tweaks, and a rejected 3D logo
A company owner asked the AI for a premium redesign of his website. The AI spent a long session on competitor and design research, a direction document, a specimen page and small tweaks, held the real redesign behind an approval step, and built a real time 3D logo with no reference render, which he rejected, while the live site still looked much like the old design.
This one went wrong. See what happened before you try it.
He left the AI running during his waiter shift and came home to a finished show episode
A waiter who produces a small game show in his spare time left the AI running with his evening list before a nine hour shift. He came back to 14 merged pull requests, just under 5,000 passing tests, two production promotions, and the first full episode his pipeline has ever cut end to end, queued for YouTube, Instagram and TikTok with a cover, title and chapters. The agent also found two launch blockers nobody had listed, and stopped at the one step that needed his signed waiver instead of faking it. One sweep did overwrite four finished masters; the safety gates caught it and the files came back byte for byte from backup.
Microsoft's Ask Microsoft Agent Expanded Across Ten Product Sites
Microsoft prototyped the Ask Microsoft web agent in an AI app Studio and went live in weeks. It moved beyond information retrieval into product evaluation and signups, then expanded across ten more product sites at two per week; customers using it visit more pages per session.
My Dot found my resume in Gmail and brought back real job listings
PCMag connected all three agents to the reviewer's Gmail and asked them to find his resume and hunt for matching jobs. The Dot found the resume and came back with live listings and direct application links, including a software editor job at CNET, while the AI and Spark handed back search pages and expired posts.
The AI guards the gate that catches his other agents drifting off-brief
Made the AI part of a deterministic quality gate for agents; the gate catches cases where an agent strays from a project's constraints.
The AI set up its own hourly PR watch and ran it for 3.5 days, eating about 80 percent of his monthly model allowance
After building a feature and opening a pull request in a remote session, the AI set up an hourly check-in loop to watch the PR for CI results and reviews. Nobody asked for monitoring. Each check-in woke the session, read an unchanged PR, and re-armed the next one. The loop ran about 3.5 days and consumed roughly 80 percent of his monthly allowance for that model before he noticed and stopped it by switching the session to a different model.
This one went wrong. See what happened before you try it.
Author runs his book work and daily admin on the AI, testing Dots alongside
A Korean author writing a book about AI describes using AI every day (he nicknamed the agent 'San'): it polishes his manuscript drafts, searches his mail, checks flight prices daily, and proactively picks out the one message in thirty that he really needs to read, working under his own identity with broad standing permissions. Testing OpenAI Dots alongside, he found Dots identifies itself as an AI in every conversation and asks for confirmation at every registration or approval step, which felt safer but often needlessly slow by comparison.
An invoice reader matches law firm bills to case codes and queues the unsure ones for a human
He built an invoice processor for a small law firm: PDFs arrive by email, get read with OCR, matched line by line to case codes, and pushed into the billing system. Anything it is unsure about goes to a manual review queue with a screenshot, and months of edge cases like 8s read as 3s went into its rules.
Two days of planning bought a 2-hour build of a high-risk feature
Spent two days planning, then the LLM built a complex high-risk feature in under 2 hours, putting deployment at 4 days instead of about 4 weeks.
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.