In this week’s roundup, I dive into the fascinating use of Large Language Models (LLMs) in predicting financial market trends—yes, it’s as complex as it sounds! Also, I share a nostalgic piece on how it feels like we’ve stopped creating things people truly want. And for a dose of fun and innovation, check out my journey in building a quad-motor electric go-kart from scratch; it finally works! Join me in exploring these diverse topics.

• Financial Market Applications of LLMs: Not surprisingly, quantitative traders have asked: can we turn these models into the next price or trade prediction [1,9,10]? That is, rather than modeling sequences of words, can we model sequences of prices or trades. This turns out to be an interesting line of inquiry that reveals much about both generative AI and financial time series modeling. Be warned this will get wonky.
• We’ve stopped making things anyone wants: I’m getting older, I’m definitely getting older (everyone is), but I remember when we made things that users wanted. We don’t seem to doing much of that anymore.
• My Quad-Motor Electric Go-Kart Finally Works: Electric go-karts aren’t uncommon, but I’ve personally never seen a go-kart with an electric motor on each wheel. If you read the last edition of this series, you’ll know my attempt at cheap kart suspension didn’t work. This time, I fix that. I also get this machine moving for the first time under its own power. Spoiler alert: It’s a monster.