Thursday, December 12, 2024

A deep dive into AI scaling laws, including an outline of the old pre-training trends as well as the new scaling trends for post-training and inference time (SemiAnalysis)

SemiAnalysis:
A deep dive into AI scaling laws, including an outline of the old pre-training trends as well as the new scaling trends for post-training and inference time  —  In our pursuit of becoming a better full service research firm, we've moved off Substack.  For any questions please read https://ift.tt/hSPd71Q #substack



No comments:

Post a Comment

Alibaba's DAMO Academy releases RynnBrain, an open-source foundation model to help robots perform real-world tasks like navigating rooms, trained on Qwen3-VL (Saritha Rai/Bloomberg)

Saritha Rai / Bloomberg : Alibaba's DAMO Academy releases RynnBrain, an open-source foundation model to help robots perform real-worl...