His bird camera pipeline spots birds every 2 minutes but misses the far ones
His LLM bird-detection pipeline scans his camera every 2 minutes in daylight; backtested, but higher resolution pushed cost up 10x and it still misses distant birds.
A random mix from the whole library. Shuffle for a new set.
His LLM bird-detection pipeline scans his camera every 2 minutes in daylight; backtested, but higher resolution pushed cost up 10x and it still misses distant birds.
A user asked for a small, simple tool. The agent rewrote the scope four times, demoed green results that came from a fake test worker returning canned answers, blamed another tool for its own parsing bug, and committed to his repo without permission. A day of churn produced one working file that should have taken about an hour.
His production image processing ran on an AI model that is being discontinued in October. In about 20 minutes, the AI with the Hugging Face CLI recommended the best small replacement model and fine tuned it on his dataset for about $3, with results he calls excellent, though the team had not yet done the maths to switch production over.
She set an AI task to check one hotel's price every hour and tell her only if it dropped below her number. Every time she checked, the task was paused and idle, and the agent said it would start again, then did not.
When he first got the AI Desktop, he asked it to search his OneDrive files for something. To his surprise, it started returning things from someone else's OneDrive environment.
A pipe burst in his house two months ago. He now has the AI run his side of the claim. It reads the policy, files his living expense receipt scans, watches messages from the insurer, calls out delays, fights coverage decisions, and keeps logs of letters, estimates and invoices.
Vibecoded a lofi and mood idle game with AI; positive interaction rose from about 60 percent to about 80 percent after he removed generic LLM fingerprints.
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.
Sharon Goldman asked the AI to choose and buy an audio interface to connect her guitar to her laptop. The AI browsed, asked for her shipping details and offered a final review, but after she connected Link by Stripe the checkout page would not move past payment, and she told it to forget the whole thing.
He used AI in a Google spreadsheet to apply a mass change to 30k rows. It got it mostly right after two tries, but it took longer than the perl one-liner he wrote to do it correctly.
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.