HackerTrans
TopNewTrendsCommentsPastAskShowJobs

smaddrellmander

90 karmajoined 3 месяца назад
idlemachines.co.uk

Submissions

The annotated PyTorch training loop

idlemachines.co.uk
81 points·by smaddrellmander·20 дней назад·19 comments

Mae vs. MSE: more than just the mean vs. median debate

idlemachines.co.uk
1 points·by smaddrellmander·24 дня назад·0 comments

DiffusionGemma: Discrete diffusion in a large language model

idlemachines.co.uk
3 points·by smaddrellmander·в прошлом месяце·1 comments

Heaven knows I'm perplexed now

idlemachines.co.uk
2 points·by smaddrellmander·в прошлом месяце·0 comments

Reading MAI's efficiency gain. How to pick architectures like serious people

idlemachines.co.uk
9 points·by smaddrellmander·в прошлом месяце·0 comments

MAI-Thinking-1: Building a Hill-Climbing Machine [pdf]

microsoft.ai
3 points·by smaddrellmander·в прошлом месяце·0 comments

Are contrastive losses just cross entropy all along?

idlemachines.co.uk
2 points·by smaddrellmander·в прошлом месяце·0 comments

Every token, everywhere, all at once

idlemachines.co.uk
2 points·by smaddrellmander·2 месяца назад·0 comments

The cut in the Mixture of Experts compute graph

idlemachines.co.uk
1 points·by smaddrellmander·2 месяца назад·0 comments

DeepSeek V4 from the Inside

idlemachines.co.uk
2 points·by smaddrellmander·2 месяца назад·0 comments

Softmax, can you derive the Jacobian? And should you care?

idlemachines.co.uk
134 points·by smaddrellmander·3 месяца назад·47 comments

Gemma 4 is not your standard transformer

idlemachines.co.uk
2 points·by smaddrellmander·3 месяца назад·0 comments

comments

smaddrellmander
·4 дня назад·discuss
Love this! Cute graphics and the way the balls combine is really fun. Great job.
smaddrellmander
·2 месяца назад·discuss
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.