comparing their benchmark scores is fucking nuts bro

Lacey is nuts bro😭

Rayan Cherki’s vision is actually nuts bro

If isco edit goes nuts bro

BRO, HECHICERO IS FUCKING INCREDIBLE. #ViernesEspectacularCMLL

Bro Chet is 7 fucking feet

bro this hoseok is a fucking PROBLEM.

THE NUTS ON DYLAN FUCKING HARPER

Lil bro is a fucking THUG 😭

Academic faculty comparing their research output 😅

this year is so fucking nuts bc tell me... how we're getting kate mckinnon as a gay scientist again and her partner is geena fucking davisshow more

Flow state rashford fucking nuts man😭

bro the sound design is so fucking cool

BRO THIS ANIMATED SEQUENCE IS SO FUCKING COOL

💻Tired of running so many slow, expensive benchmark evals... across every checkpoint? Try ✨BenchPress✨ at provide a few benchmark scores, then get predictions for the remaining ~100 benchmarks, with trust probabilities and calibrated 90% prediction intervals. How does this work? In his original post ( Dimitris Papailiopoulos first tried the idea as a fun question: collect model-by-benchmark scores into a matrix, find its low-rank structure, and use matrix completion to predict missing benchmark scores from a few observed ones. We expanded this into a full system: a fully audited 84-model x 133-benchmark score matrix, an optimized matrix-completion predictor, and a reliability layer for trust probabilities and 90% prediction intervals. Beyond predicting missing scores, we also suggest practical seed benchmark sets. The five-probe set {GPQA-D, HLE, Codeforces, MMLU-Pro, ARC-AGI-1} recovers the rest of a model's public score profile with a MedAE of 3.93 points. A lower-cost set {GPQA-D, MMLU-Pro, Aider Polyglot, MATH-500, AIME 2026} reaches 4.55 points. See more details below 🧵1/7 This work is with Dimitris Papailiopoulos at AI Frontiers, a boutique research lab inside Microsoft Research.show more

Comparing Messi with Ronaldo in 2026 come on bro... it’s no longer a debateshow more

who does that fucking deer think he is bro