Hacker News with Generative AI: Scaling Laws

O1: A Technical Primer – LessWrong (lesswrong.com)
TL;DR: In September 2024, OpenAI released o1, its first "reasoning model". This model exhibits remarkable test-time scaling laws, which complete a missing piece of the Bitter Lesson and open up a new axis for scaling compute. Following Rush and Ritter (2024) and Brown (2024a, 2024b), I explore four hypotheses for how o1 works and discuss some implications for future scaling and recursive self-improvement.
I want to break some laws too (snats.xyz)
I made an automated pipeline to clean data. The idea started from a paper called Minipile. This led me to a rabbit hole. If you’re careful about the data you use for training, you can break the scaling laws. Who knew being a data snob could be so rewarding?