Opus read his years-old C codebase and found 5 serious bugs immediately
The AI pointed at his years-old C codebase immediately found 5 serious bugs and told him how to fix them.
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.
The AI pointed at his years-old C codebase immediately found 5 serious bugs and told him how to fix them.
Dave Hamilton put $10,000 from a domain sale into a 90 day test and let the AI run it. The AI set a fixed trading plan, 60% crypto and 40% stocks, trades through Kraken and Alpaca, and can act after 48 hours if he does not answer.
He gets a lot of emails from customers with randomly organized spreadsheets that need to be loaded into their database. Now he can just say grab so-and-so’s email and work it. The AI does the whole conversion for him, with checks, and puts the reply in his drafts, so all he has to do is look it over and send it.
He used AI to make a Telegram channel for NHK's Documentary 72 Hours. The channel posts alerts for new episodes with video links, previews of the next episode, and titles and short write ups in Chinese.
A man who runs his own services at home sent his AI an article about a PHP security hole. The agent patched the services that had a fix, stopped the ones that did not, set up a watch for new fixes, and updated and restarted nearly everything as fixes landed through the day.
He had a pile of old laptops he had never gone through. The AI helped pull the hard drives, read them, and look for less obvious sources like old chat logs, then built a screen that makes it all searchable. He found personal history he had forgotten about.
While debugging an OCR problem, the AI deleted his entire training data repo, weeks of captured data, saying the data was the problem. He restored it from a backup that happened to sit in a pull request.
The AI in Antigravity built an Enigma decryption program, fetched repos, ran an 82M combination scan and decrypted the message in about 45 minutes.
The AI saw that Caddy was nearly out of memory on his service, checked the traffic, and found bots hitting IP addresses his customers never use. It tested a block through a live failover, applied it with no downtime, wrote it up, and merged the pull request.
A father had the AI build a standard writing practice template for his daughter, who reads well ahead of her level but still writes basic, sound-it-out spelling. The AI also makes the picture for each sheet. She writes about the picture, colors it, and uses a printed reminder sheet that shows the different ways to spell the same sounds.
His AI skill was built from his earlier renovation sessions and loads on its own whenever he mentions the house, the contractor or an invoice. It carries the project context, the key contract clauses and where every file lives, holds a step by step invoice verification checklist, and drafts his emails in a language that is not his own, with a pre-send check that every number matches the project register.
A session generated a Word document with a script. The user then edited the document in Word for about 40 minutes and saved. When he asked for one more change, the session re-ran its script, which rebuilt the whole file from its older in-memory content and replaced the file on disk. His 40 minutes of edits were unrecoverable, because the write went through the shell, where the tool’s read-before-write protection does not apply.
After fighting a slow, buggy AI setup for office work, a user switched to the AI and quickly had a bookkeeping workflow running: connected to Xero, it reads his email and finds the invoices in no time instead of him digging through threads at month-end.
His dryer broke and he asked the AI for help instead of calling a repair company. It worked out the timer dial was broken, ordered the right $30 part on Amazon, which came overnight, and then walked him through the repair step by step, tools and all.
LLMs decompiled Civilization 1 into reconstructed C source that builds with the original toolchain and matches the original executable byte-for-byte except a four-byte patch correction (finished result report).
A father's son grew his hair since Covid and cut it to donate to a charity that makes wigs for children with cancer. The father kept putting off making a poster, then gave the AI a couple of photos and a video link and it built the poster while he worked. His boss put it up, workmates pledged enough to fund the wig, 250 pounds. Later, from the car, he voice prompted the AI to remake the poster in his son's words for the boy's school, and forwarded it on WhatsApp when they arrived.
An engineer had just had the AI reapply local, uncommitted code changes. Separately, a GitHub Actions run he had triggered against production was mid-flight, in the middle of creating a replication subscription on a live Postgres server. He said undo the work it just started, meaning the local edits. The AI read it as the production run and cancelled it mid-statement, leaving whatever partial state the kill created. The local edits were not touched until he clarified.
He connected the AI to NetBox so the agent does his home lab documentation. The AI scans his network from a tools server, enters hosts, VLANs, virtual machines and Proxmox cluster details into NetBox, logs pending updates in journal entries before and after they are applied, and now runs an incremental scan every day at 02:00 UTC so the inventory does not go stale.
A screen-capture reel from someone (Irene, 'Smart American Life', 59 followers) shows a Chinese-language message documenting an AI negotiation with a retention rep named Kia: $1,440 total savings via a $20/month discount for 24 months, a $10/month autopay discount, 3 months of free internet, and a new rate of $45/month down from $75/month plus tax. Presented as a US life-hack with itemized terms.
He lost most of his vision this year to a rare genetic condition. With the AI’s help he built a tool that lets him play games again, designed so other people with sight loss can use it comfortably too; he plans to release it free with the source open once it is ready.
A trading-card collector named Marcus, overwhelmed by 75 cards he didn't know how to price, photographed each card with his phone in a Facebook reel demo; the AI cataloged them, enhanced the photos and lighting, and generated eBay listings with prices set from market data.
The AI as CAD tutor and direct python generation failed, then the AI implemented a bespoke DSL that produced exactly the DXF geometry he wanted.
Used the AI to build an omit needless words app and used it to edit a document he is working on, accepting about a third of its suggestions.
He self hosts and connected his 3D printer to the AI through a small bridge he runs on his NAS. Now he can ask how a print is going and get progress, temperatures and time left. The AI also watches the printer's smart plug and messages him when a print finishes.
A dad of two under two steered the AI to build Forkcast, a weekly meal-planning and calorie-tracking web app, because existing apps plan only a day at a time. It generates his grocery list from the week's plan and imports recipes from photos and labels for his 90-day weight-loss challenge.
Answering a thread asking for the coolest thing people had done with AI, he reports two cancellations. The first: The AI cancelled his Adobe membership and got $400 back in membership fees. The comment is short and gives no steps, so it is recorded at modest specificity; the second cancellation from the same comment is a separate record.
Alex Willen gave his AI (named Sierra) a flexible return-leg search, Vegas to San Diego. It first offered only JSX, Southwest and Frontier, then, told he had many Amex points, returned two Alaska flights and one American flight with a layover and wrongly advised that none of the carriers are Amex transfer partners so booking with points would be a bad idea, missing that points transfer to British Airways to book partner flights, something the AI had taught him.
He needed quotes for a seasonal tire swap, with the winter set already on rims, and did not want a day of phone tag. He connected the AI to a calling service with a script: price with tax, proper lifting pucks for his car, torque to spec at 175 Nm, and openings after mid November. The first call failed because the shop asked where he was and the agent had no answer. The callback with his area in the intro worked: $120 plus tax, pucks and torque confirmed. Other calls came back at $50 tax in for a mobile service and $168 plus tax, and one went to voicemail. Every call produced a full transcript. He then set 18 more shop calls for the next day and updated all of them at once with four facts he had missed the first time.
A store whose checkout is a web endpoint got its first agent order: an AI agent running on the AI, given a one line instruction by a person to buy a black t-shirt in size small and pay from its own wallet without asking approval, did the whole purchase in 6 web calls. It paid $29.94 in USDC, the payment settled in 2 seconds, and 16 minutes later the shirt was in production with the printer.
A man asked the AI to schedule daily backups of his agent folder with a careful keeping rule: three weeks of daily copies, four Saturday copies, and the first copy of each month. The AI also copies them to a storage server in a different building and runs a health check that alerts him only when something is failing.
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.