Machine Learning Street Talk · Wednesday, September 23, 2026
Frank Hutter, CEO of Prolaps, discusses how deep learning models, specifically TPEN, are now dramatically outperforming traditional models like CatBoost and XGBoost for tabular data. He explains that TPEN represents a natural progression of AutoML, learning an entire algorithm executable in a forward pass.
“And that is something that, uh, didn't use to work, and with, uh, TPEN, we actually made it work and, uh, yeah, are scaling this up, foundation models, and, uh, really excited to revolutionize as well.”
“So if you were to throw this into an LLM, you would have a billion, um, elements and you'd need to tokenize each of these numbers, so that would maybe be three for tokens each, so you have three for billion tokens in your context and LLMs wouldn't be very happy there.”