Andrej Karpathy (@karpathy) on Xknowledge-baseMar 9, 2026By Team M37Labshttps://x.com/karpathy/status/2029701092347630069?s=46X (formerly Twitter)Andrej Karpathy (@karpathy) on Xnanochat now trains GPT-2 capability model in just 2 hours on a single 8XH100 node (down from ~3 hours 1 month ago). Getting a lot closer to ~interactive! A bunch of tuning and features (fp8) went in but the biggest difference was a switch of the dataset from FineWeb-edu tox.com
