BarraHome/Qwen3.5-27B-Claude-4.6-Opus-FP8-Dynamic Text Generation • 27B • Updated 21 days ago • 269
BarraHome/Qwen3.5-27B-Claude-4.6-Opus-FP8-Dynamic Text Generation • 27B • Updated 21 days ago • 269
stepfun-ai/Step-3.5-Flash Text Generation • 199B • Updated about 1 month ago • 138k • • 777
view post Post 348 Hey if you're reading this and happen to be one of the guys training frontier llms, please penalize 404 urls in your reward functions. Happens too often that these models memorize / make up non-existing url paths and get away with it See translation 1 reply · 🔥 1 1 + Reply