Stories by nyrikki

Ask HN: PIIA Carve Outs

Systemd, Vsock, & OpenSSH-Server

Mind the Gap: Deep Learning Doesn't Learn Deeply

Beyond Semantics: Unreasonable Effectiveness of Reasonless Intermediate Tokens

Do Think Tags Help LLMs Plan?

(How) Do reasoning models reason?

Equivalence of the Frame and Halting Problems (2020) [pdf]

GAO Agile Assessment Guide (2023)

Why Are Sensitive Functions Hard for Transformers?

LLMs can't self-correct in reasoning tasks, DeepMind study finds