An LLM reverse engineered a camera with disassembly tools and got its keys and boot code
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
429 new ideas this week
Level up how you use AI
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 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.
The AI cracked an Enigma message after scanning 82 million combinations in 45 minutes
The AI in Antigravity built an Enigma decryption program, fetched repos, ran an 82M combination scan and decrypted the message in about 45 minutes.
45 minsaved
I cleared a backlog of over 50 blog drafts with eight agents
He blogs on his own and set up an 8 member virtual publishing desk in Antigravity, with agents reviewing each other and strict gates before anything goes live. The desk worked through his backlog of more than 50 drafts.
Handled doctor's-office admin in ~5 minutes: emailed the office, left a voicemail,
X poster someone had the AI do doctor's-office admin in about 5 minutes: it emailed the doctor's office, left a voicemail, filled out new-patient paperwork, and created a calendar entry.
Agent logged in and filed the firm EPF contribution itself
An audit partner runs his accounting firm on an agent platform wired to its own live data. In the session the agent pulls the credentials from a vault, logs into the KWSP i-Akaun portal, and submits the EPF contribution, with the partner reviewing the figures before payment.
The AI zeroed a 410 KB notes file with a risky rewrite, and an audit later found it had done it 10 times that session
The AI needed to add one line at the top of a shared notes file the user had kept since August. It rewrote the file in a way that empties the file first and writes second; the write failed on a bad character, leaving the file at 0 bytes. The file survived only because an outside backup existed. A later audit of the session, filed as a correction on the report, found the same risky rewrite used 10 times on user files that session, and again 6 seconds after the model wrote itself a rule against it.
This one went wrong. See what happened before you try it.
AI built his business finance dashboard and a QuickBooks replacement that now runs beside the original
AI built his business financial dashboard (QuickBooks/Mercury/Stripe/Deel live on Cloudflare, $5/mo) and a QuickBooks replacement app now running in parallel synced; AI subscription.
$5a month
A 7am stock screener flags the morning's biggest movers for me
A second daily run at 7am screens stocks with high relative volume among the day's percent gainers and flags each one red, amber or green for his trading. He reads the flags and makes his own calls.
Suggested Mexico City for a trip under 6 hours from NYC, then
Elona told her AI 'the AI' her vacation criteria; it proposed Mexico City and offered to book everything. She then requested an iconic luxury property, a direct flight on her preferred airline, and maximized credit-card rewards.
The AI triages his user bug reports and tells both sides what happens next
The AI told to find a user's bug, decide user error vs bug, notify the user and tell the developer what to fix; the developer replied in 15 minutes asking if the fix was wanted today or Tuesday.
Planned and booked a spontaneous getaway in Spanish: compared destinations, flights, and
A first-person account of testing the AI to fully plan and book a spontaneous trip without doing research: an open-ended goal (good food, beautiful stay, minimal effort). The AI compared destinations, flights, and hotels, noticed the author's saved Instagram folder for Mexico City, suggested ways to use points and travel benefits, and organized everything into a bookable plan — presented as Part 1 of a series.
An AI bot called Zara interviewed me for a journalism job
She applied for a journalism job and was interviewed by an AI bot called Zara. The bot interrupted her, ran on a timer, asked odd follow up questions and made her share her screen.
This one went wrong. See what happened before you try it.
The AI ran their 14 day Japan trip live, re-timing days from his phone
A couple spent 14 days in Kyoto, Hakone and Tokyo with AI as their travel assistant. Before the trip it grilled him one question at a time instead of handing over a plan, and built a private offline trip page for their phones with day cards, booking codes, train guides and taxi cards showing the hotel address in Japanese. During the trip he ran it from his phone: after they caught a later train he asked for the day to be re-timed and got new times, an updated app and moved calendar events in a couple of minutes. One stop was added without anyone checking it was open, and it was not; after that every stop got checked on the venue's own site first.
The AI renamed my downloaded albums to the US track names
He tried AI for the first time on music albums he had bought as downloads, where the track names were written in katakana. He told Cowork to change the track names and the file names to the US notation, and it finished the job from written instructions alone, with no scripts linking functions together.
The AI made me a spreadsheet of 65 cars that fit what I want next
He had the AI build an Excel sheet of car models that could work as his next car, using his own list of must haves. The sheet came back with 65 options, with size, comfort and whether each one comes as an automatic.
Catch my duplicate Southwest tickets and save me about $1,200
Creator Jen Lehner says in an Oct 19 Facebook reel that Instinct proactively texted her that she had accidentally booked duplicate Southwest Airlines tickets for herself and her daughter out of St. Louis on both Friday and Saturday. She confirmed the booking, it was canceled in time, and she received a full refund saving approximately $1,200.
$1,200
437 subagents reviewing in yolo mode forced him to build his own spending rules
437 the AI subagents ran adversarial reviews in yolo mode with repeated duplicate checks, forcing him to build his own spending and observability rules.
This one went wrong. See what happened before you try it.
Fable built the tiny text editor he now uses as his main editor, in about 2 days
Fable built him a tiny, fast text editor in about 2 days that he uses as his primary editor, plus a key-bound note-taking interface in his Notes folder.
Build me an earnings and expenses tracker for my student budget
An 18-year-old first-year college student with a part-time job says he told the AI his weekly pay and it created an 'Earnings & Expenses' budget tracker showing earned, spent and net, plus a purchase log (Loblaws, Tim Hortons, Presto). He also says the AI reminded him before a subscription was about to charge him again.
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.