this is f*cking wild. same prompt, two completely different worlds
one model built a rainy night city racer - tight, atmospheric, focused
the other went sunset highway with a truck in the way - looser, more cinematic, different physics and pacing
benchmarks would call both “good enough.” but the gap isn’t accuracy. it’s taste
one model edits itself down. the other keeps adding until it feels finished
exactly the thing the piece I’m quoting keeps hammering: there’s no single winner, just who wins at what - and whether you can live with the cost and the side effects
so which version would you actually ship? the restrained one or the one that keeps going?
(save the article if you want the full map of who actually wins coding / reasoning / video / cost right now)
26-YEAR-OLD GIRL QUIT HER JOB AND BUILT A SMALL SOCIAL NETWORK FOR NYC. 31,000 USERS IN 4 MONTHS. NOW IT MAKES $18,400/MO FROM LOCAL SHOPS
she didn’t try to build another Instagram. she built a tiny app for one obsessed niche: people who save cafes, share lists, follow local taste, and discover places before they go viral on TikTok
the product is simple. profiles, posts, likes, saved lists, search, comments, and a feed. that is basically every social network at the core. the hard part was needing 5 engineers to make it work
Claude Code changes that. one person can now build auth, database, feed logic, profiles, follow system, storage, notifications, and deployment with supabase and vercel instead of hiring a full team
the money is not from ads. cafes pay $199/month to claim their page, boost new menu drops, see which lists saved them, and post local offers. power users pay $8/month for private maps and early city guides
most people still think social networks need millions of users. she proved the opposite. 10,000 people in one niche can be worth more than 100,000 random users scrolling for nothing
small social networks are the new local media businesses. Claude Code just made them cheap enough for one person to start one from a laptop
holy sh*t. Your AI can now keep a second brain that builds itself. Karpathy’s pattern, running on Grok Bot
stop explaining yourself from scratch every chat.
three bots share one group chat, each with its own memory:
the reader takes in whatever you drop (links, PDFs, voice notes) and never edits it
the librarian updates every wiki page that source touches, usually 10 to 15 pages
the checker works at night and hunts for contradictions, stale claims and pages with no links pointing to them
→ you ask something: the answer gets saved as a page, so the brain grows from use, not only from reading
→ new info conflicts with an old page: the checker tags you instead of overwriting it
→ 30 days without a fresh source: the page is marked unconfirmed
a second brain can sound sure and still remember the wrong thing
Reader collects. Librarian writes. Checker doubts.
every page has to show:
the claim
the source it came from
the date it was last confirmed
paste this into Grok Bot:
“Build me a second brain with three bots in one group chat. Keep my sources untouched in raw/, maintain wiki/ yourself, file good answers back as pages and run a nightly check for contradictions. Show me the structure first. Do not create anything until I confirm”
start with one topic you actually work on, not your whole life
full setup below