Read the original: Arthur Mensch· arthurmensch·Published Oct 6, 9:29 AM ET· 3d agoAI score48/100That one took some groundwork. Trained and served on our own compute, and RL shows no sign of saturationRead the original x.comSource: Arthur Mensch · x.comMultimodal AIOpen-source ecosystemDeployment & engineeringModel releasesEvals & benchmarks#Model release#Eval/Benchmark#Multimodal