An agent reverse engineered a CAD tool's interface to dodge its API pricing
Made Astra reverse-engineer Onshape's UI to build a middle-man extension exposing an API that bypasses the official API pricing, now used for AI CAD with AI and the AI.
A random mix from the whole library. Shuffle for a new set.
Made Astra reverse-engineer Onshape's UI to build a middle-man extension exposing an API that bypasses the official API pricing, now used for AI CAD with AI and the AI.
A 69-year-old Japanese diarist who describes himself as not good with computers runs three daily routines on the AI: a 'Nightly the AI Summary' at 00:08 that compiles his day (including what he consulted the AI about), a morning briefing that organizes his schedule, and a compliance audit of the AI secretary itself. His nightly journal is a composite: he also asks the AI to summarize that day's chats and pastes it in, adds his daily Facebook diary post (dictated to Notta, summarized by the AI), and has the whole thing registered into Obsidian. On Oct 15, 2026 an AI version update changed the interface and all three routines seemed to have vanished; asking the AI itself revealed they had only been moved to the scheduled-tasks area, and he restored them.
He upgraded Proxmox on 3 nodes, with about 30 containers moving from Debian 12 to Debian 13, and put Opus at the wheel. The upgrade finished with zero drama.
He spent about 5 minutes picking the mods he wanted for GTA4. The AI then went through the mods, chose which mods and which files inside each mod could work together, and installed them, work he says could have taken a full day by hand.
Reverse engineered the Insta360 Studio binary with AI and wrote a shim for his AMD iGPU so the app is usable.
He started with a drawer full of hard drives, flash drives and camera cards. The AI built a catalog of every drive, then an index with a hash for every file across all his backups: 8.1 million files, 3.6 million of them unique, going back about 20 years.
One of eight hands-on tests run on the reviewer's real accounts; the AI scored 42.5/47 overall across the gauntlet.
The AI built and optimized his local decision engine for his private image organizer, reaching just under 85 percent accuracy across 500 validation prompts with sub-second responses.
A local Qwen model on his home server pulls his RSS and social feeds, release notes and papers, scores each item against an interest profile he keeps by hand, and writes a one line summary. Nothing leaves the machine. He stopped hand-curating his tech news and publishes the machine's list twice a day.
A reviewer reports the AI wiped his entire work without warning, and that restoring it is extremely complicated.
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.