Yatong Chen

yatongchen.bsky.social

03 July 2026 14:57

LLM leaderboards aren't passive measurements — they're mechanisms that create incentives! Why does the current evaluation protocol reward "benchmaxxing": post-training for the benchmark without improving model capability? Our #ICML2026 paper gives a theoretical answer! 🧵

Nikhil Garg

nkgarg.bsky.social

03 July 2026 14:56

1/7 Excited to share EconCSLib: a Lean library/workflow. Our vision is to enable researchers who don't know Lean to formalize their Applied Modeling papers. Why? I, and most theorists, are terrified of fatal mistakes in our papers Paper: arxiv.org/abs/2606.13306 Project: gargnikhil.com/EconCSLib/

Nikhil Garg

nkgarg.bsky.social

02 July 2026 17:49

Very cool! This question of "how do we audit + organize against stochastic algorithms when we have to collect data from individuals" is a super important and pressing question

Juba Ziani

jubaz.bsky.social

13 June 2026 08:39

Is anyone still alive here? Outside of @ccanonne.github.io I mean

Clément Canonne

ccanonne.github.io

08 June 2026 07:40

After the Odyssey, Christopher Nolan is working on an adaptation of the myth of Sisyphus. According to sources, they've already cast The Rock