Mae vs. MSE: more than just the mean vs. median debateidlemachines.co.uk1 ポイント·投稿者 smaddrellmander·23 日前·0 コメント
DiffusionGemma: Discrete diffusion in a large language modelidlemachines.co.uk3 ポイント·投稿者 smaddrellmander·先月·1 コメント
Reading MAI's efficiency gain. How to pick architectures like serious peopleidlemachines.co.uk9 ポイント·投稿者 smaddrellmander·先月·0 コメント
MAI-Thinking-1: Building a Hill-Climbing Machine [pdf]microsoft.ai3 ポイント·投稿者 smaddrellmander·先月·0 コメント
Are contrastive losses just cross entropy all along?idlemachines.co.uk2 ポイント·投稿者 smaddrellmander·先月·0 コメント
The cut in the Mixture of Experts compute graphidlemachines.co.uk1 ポイント·投稿者 smaddrellmander·2 か月前·0 コメント
Softmax, can you derive the Jacobian? And should you care?idlemachines.co.uk134 ポイント·投稿者 smaddrellmander·3 か月前·47 コメント
smaddrellmander·4 日前·議論Love this! Cute graphics and the way the balls combine is really fun. Great job.
smaddrellmander·2 か月前·議論A similar vein, asking why in PRs. Most people don’t do the above, and asking why when it doesn’t make sense really helps understanding what your colleagues are actually thinking. Helps create a unified perspective on the codebase.