I'm jealous that this does not refer to us: "I met an AI superforecaster startup founder who told me his AI had turned $35 into $2 million on Kalshi over seven months."
I also talked to him and 100% believe he was able to pull this off. And it was on 10,000+ trades so it wasn't luck.
After 20+ years in the market, today I learned: "The S&P 500 is a float-adjusted, market-capitalization-weighted index."
So presumably an S&P 500 index fund is not disadvantaged, since it is tracking a float-adjusted index, i.e. the weight of SpaceX will be tiny if its float is tiny.
I can get more accurate forecasts by having distinct agents do different research tasks, summarize, and then feed those summaries to an agent that uses judgment to forecast.
Is there any lesson here for non-devs (like me) who are using CC to write some pretty long, gnarly notebooks. The problem I have recently run into is that CC vibe codes really long code with lots of checks. But, then when I want to modify it, CC has more code to read and it gets overwhelmed. If it didn't include as many checks to begin with, it would be easier to understand what is going on.
Any advice? Have you seen this with code in production?
I also talked to him and 100% believe he was able to pull this off. And it was on 10,000+ trades so it wasn't luck.