Why do linear models sometimes outperform much more complicated modelling frameworks on the #numerai tournament? New forum post.
https://t.co/Ggbj7ZcUcR
It's hype time. We built a platform where ML models compete to predict future performance of Hyperliquid perps.
Interactive scores, real-time leaderboards, a meta-model ensemble, AI agent integration, and... a flight simulator.
@Lingster888@CrowdCent If you evaluate on every era rather than every 30 (for 30d returns) you will underestimate your volatility because of the overlaps
earlier this year, i said that if your partner dresses up for dinner or a date, you should too, so that you make them feel more comfortable. and tons of guys objected. is putting a little effort into an outfit so onerous that you can't consider your partner's feelings?
@jeethu@quant_questions SPOILER: in the 20:20 case you can let P(tie)=x. P(A) = P(B) = (1-x)/2. One more coin flip for player A only effects the outcome if they get heads and it was already tied so new P(A) = (1-x)/2 + x/2 = 0.5
We are rolling out Early Access to
WORLD's FIRST AI TUTOR trained on your own course and content, it is powered by ChatGPT and developed
using @langchain by @hwchase17
Interactive learning at your own pace with dynamic quizzes.
#ai#nocode#buildinpublic#ChatGPT