I see copy trading gaining momentum, just give us a working strategy and we will just mirror it
No competition in tradingc, we are all fighting against sapa
Claude 5.0 built a Chinese girl a trading bot.
skip to 0:08 look at her journal, bot easily earns your monthly salary in a couple of days.
how it works:
the bot runs mean reversion on s&p 500 and nasdaq on 15-min candles, catching the small overextensions indices make every few hours. on bitcoin it switches to momentum breakouts on the 1-hour crypto trends harder than indices, so you ride the move instead of fading it. gold and oil get a slower trend-following layer on the 4-hour, because commodities move in cleaner waves and you don't want noise from intraday whipsaws.
position sizing is ATR-based per instrument, so a quiet day on gold gets a bigger size than a volatile day on bitcoin - risk stays constant even when volatility doesn't. every trade has a hard 1% stop, no exceptions, no "let me give it room." and there's a correlation filter on top: if s&p and nasdaq are already long, it won't pile into another risk-on asset and double the real exposure.
claude code writes and updates the logic. the bot just executes.
then claude cowork sends her two messages a day:
- 7am: what's happening in the market
- 9pm: how did the bot do
that's the whole job. two messages. five instruments. zero screen time.
manually she could only watch one chart at a time. this thing watches five. doesn't sleep. doesn't tilt. doesn't revenge trade at 2am.
what used to need a team of quants and a $200k bloomberg terminal now runs on a laptop and claude.
And your friend is still trading manually and is constantly in the red.
save this and read the article in the comments below to write your own bot using Claude
Stop saying: I have not received the email.
Start saying: I am still expecting the email.
Stop: I cannot open the document.
Start: The document is password-protected. Can you share access?
See?
Same information. Completely different energy.
AI will make it extremely easy for African founders to build.
The hardest part, and the one thing I really want more people to work on, will be distribution. Go out and find customers, get money, prove that whatever you're building is actually worth building, before going to raise VC money.