Press Space to continue
During Recursive Self-Improvement (RSI)
Press Space to continue
Super impressive. Congrats! And maybe suggests that during RSI, the automated AI researchers will be less bottlenecked by compute than we might naively think.
magicailabs@magicailabsSep 8
Frontier pretraining is said to be a big-lab-only game. We don’t have 100k chips yet, so there’s only one way: algorithmic efficiency. Our new recipe matches DeepSeek V4 Pro’s pretrain using 50x less compute – that’s roughly half the FLOPs used for GPT3, or ~$0.5M on GB200. https://t.co/uBs5o5Arsu