A week of the AI tuning tripled his local model's speed on old datacentre cards
The AI had been optimizing llama.cpp for about a week and reached about 300 tokens per second decode on two V100s.
A random mix from the whole library. Shuffle for a new set.
The AI had been optimizing llama.cpp for about a week and reached about 300 tokens per second decode on two V100s.
She pulled 50 local business leads for $0.44 and used AI to pick the ones with good reviews and a weak web presence. Then she built and published a live web app for one of them in one sitting, and says the hard part now is turning businesses like that into paying clients.
Runs an AI agent continuously scanning a WordPress VM and its host for intrusion signs, costing a few dollars a day billed to the customer.
The AI spent a couple of hours going through about 250 of her past newsletters and repurposing them. Her blog is now live with that material.
The AI knocked out a side-project prototype in an afternoon, which immediately showed the product interaction was a dead end and saved months of further building.
His todo list outgrew his Obsidian file, so he moved about 300 issues into Linear through the AI. He then refined the roadmap by talking with AI while driving.
Runs a local model as administrator for their Asterisk PBX and RADIUS server and to judge CCTV footage for security notifications, with good results so far.
The AI cuts his video in DaVinci Resolve by editing a subtitle export with IntelliScript; Resolve then produces the cut version; works well.
He points an AI project at a folder of case files. When a new court filing arrives, he saves it to the folder and has the AI read it and draft the response. He also uses it for file organising, reading PDFs, transcribing audio and filling forms, and says the work became far easier.
A developer told the AI to repair his stock-options analysis software working only on copies; when the mirror-rebuild tool failed, the agent wrote its own Python cleanup script that treated 614 Windows directory junctions inside the temp mirror as ordinary folders and deleted 48,218 live files in 103 seconds. The sweep also emptied the Git object store, leaving an index that listed 7,221 paths whose contents were unrecoverable.
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.