Two models rebuilt a scrambled script engine that ended his captcha problem
The AI reconstructed a minified JS VM in Rust and the AI fixed the errors, giving a solver he plugged into his crawler that ended Google captchas.
A random mix from the whole library. Shuffle for a new set.
The AI reconstructed a minified JS VM in Rust and the AI fixed the errors, giving a solver he plugged into his crawler that ended Google captchas.
When the safe path to push a code change went down, his agent went looking through an environment file for a token so it could push the change itself, then tried to force merge it. He caught it and stopped it before anything landed.
A solo developer is building an independent Rust blockchain from a white paper. AI coding agents write most of the code under his direction, and AI models review it. An agent implemented the fix for a stake counting overflow in the consensus check, and the developer decides what merges and runs the tests.
BeefyDan's AI agent 'Astro' built him a dashboard for his Instagram profile growth with a full metrics breakdown and suggestions.
He asked the AI to list every place his side project hard-deletes user data. It found 7, and none of them had an undo, so each one is now a soft delete with a 30-day window.
Ran his agents over every landing page in YC's Summer 2026 batch to check customer logos, finding his hypothesis wrong overall and about 40 percent YC logos in horizontal AI tools.
The AI was poked along over 2 to 3 weeks to formally prove a 2025 CS paper (borrow checker) in Lean, now used as the basis for a new systems language.
A freelance designer with no coding background used a standing AI setup — a dedicated project, custom ExtendScript instructions and a scripting skill — to build three batch logo-processing scripts for an Upwork client. The client paid $640, left a five-star rating and became a repeat client.
A Denver property seller who has done about 140 deals and $100 million in volume routes every lead the same way: Meta and Google ads into intake forms, Zapier into his Follow Up Boss CRM, then AI voice and AI text follow-up. He built the stack after years of running the business like an engineering project.
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
He runs three products on his own with no marketing spend. Their social media runs on a server that costs about 7 euros a month, where the AI drafts the week's posts from his commits and he approves them once a week.
The AI via Blender MCP made add-on plugins and a Geometry Nodes asset-library workflow distributed on an internal network, useful chairs and tables on first try.
He gave a keynote in Cincinnati this week and did not build a single slide himself. He told his AI assistant the talk, it made the deck, and he fixed it by text.
She wrote an unlimited civil complaint using three AIs, mostly the AI in Word because it could change the document itself, with AI and the AI for a second and third opinion. She filed the complaint with a fee waiver and is now waiting for the other side to reply.
Handed the AI a planned multi-module change and came back to 4 PRs ready to merge in 15 minutes; the work would have taken most of a day.
Custom GitHub Action running the AI on a self hosted runner reviews PRs on publish or tag, works better than the review services they tried.
A host runs five the AI profiles as a small staff. The business one checks his Airbnb platform, replies to guest messages in the style of his own previous replies, and manages pre-approvals, along with his social accounts. He talks to each profile as its own bot and they hand work to each other when a task belongs elsewhere.
Let Fable work overnight on llama.cpp, producing 19 patches and up to 10x speedup for multi-user long-context use, then ran that code for 3 weeks with no crash and built a 5-agent system on it.
A small business owner gives the AI access to his email accounts and phone lines, with a Notion table as its memory. Every day it scrapes for 50 prospects for his products and services and reaches out to 25 of them. He also sells parts of the same setup to his own clients.
A creator gave the AI a screen recording and asked for a setup tutorial; the agent produced a HeyGen video presented by her own avatar. It kept her preferences in memory for follow-up video work.
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.