Astra made his 32-bit game run on a modern Mac within minutes by replacing its runtime
Astra made his 32-bit game Aviary Attorney run on modern macOS within minutes by replacing its runtime.
A random mix from the whole library. Shuffle for a new set.
Hobbies
Making things, learning and having fun · 960 ideasAI designed and routed about 15 of his circuit boards, with known mistakes in the pile
AI through tscircuit and OpenAI models designed and autorouted about 15 ordered RP2040 and ESP32 PCB designs; known mistakes include improperly rotated connectors and routing loops.
This only partly worked. Worth knowing before you try it.
Built a trade-alpha dashboard from confirmation emails benchmarked against SPY
Someone had the AI build a trade-alpha dashboard from his trade confirmation emails and benchmark the results against SPY. The agent turned scattered confirmations into a performance benchmark.
His Blender agent built and animated a spaceship, then caught its own thrusters firing into the ship and rebuilt them
A man built a chat copilot inside Blender in a day, at a total cost of $7.18, then gave it 5 sentences. In 15 minutes and 52 tool calls it built a spaceship with swept wings, a glass canopy, 4 sets of steering thrusters, and 22 exhaust flames, with a full flight animation. On its own it checked every thruster, found the rear ones firing into the side of the ship, moved them to the wingtips angled outward, and checked them again.
The AI spotted a wrongly-set device alarm within minutes from the log
A DO alarm was accidentally set to a past time and retriggered immediately; the AI caught it within a couple of minutes from its log tail.
I talked to GPT Astra and it modeled and 3D printed a weed holder
He used GPT-6 Astra to model a small weed holder and 3D print it. Talking to the computer and getting a real object back felt to him like a Star Trek replicator.
Researched three coffee shops with opening hours in ~2.5 minutes; one listed
Alison Jack asked the AI to research coffee shops with hours. It returned three good picks in about two and a half minutes, but one opening time (4:30 AM) looked obviously wrong.
This only partly worked. Worth knowing before you try it.
Pulled 2,556 saved Facebook/Instagram reels and posts into a categorized, searchable Notion
Josh Collier ('Fractional AI Officer', 7.6K followers) showed the AI connected to Notion pulling his entire archive of 2,556 saved FB/IG items into a 'Saved Library' database with category, platform, type, author, link, hashtags, date, and full caption text. Breakdown read aloud: Exercise 562, Business 231, Mindset 221, Finance 144, Golf 137, Faith 97, AI 91, plus Lifestyle/Tech/Health and ~1,000 older captionless saves in 'Other.' He called it his AI now 'knowing' everything he saved.
An LLM maintains his research document and the pipeline that rebuilds its figures
An LLM maintains his org and LaTeX work document, an external library and CLI, and a Makefile and Snakemake pipeline that regenerates content and figures and puts numerical results into LaTeX macros.
Every domain he buys, his agent SSHes in and sets the whole thing up
Keeps his Namecheap API key on his server so every time he buys a domain he tells his AI agent to SSH in and set everything up.
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.