HackerTrans
TopNewTrendsCommentsPastAskShowJobs

smaddrellmander

90 karmajoined 3 माह पहले
idlemachines.co.uk

Submissions

The annotated PyTorch training loop

idlemachines.co.uk
81 points·by smaddrellmander·20 दिन पहले·19 comments

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

idlemachines.co.uk
1 points·by smaddrellmander·24 दिन पहले·0 comments

DiffusionGemma: Discrete diffusion in a large language model

idlemachines.co.uk
3 points·by smaddrellmander·पिछला माह·1 comments

Heaven knows I'm perplexed now

idlemachines.co.uk
2 points·by smaddrellmander·पिछला माह·0 comments

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

idlemachines.co.uk
9 points·by smaddrellmander·पिछला माह·0 comments

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

microsoft.ai
3 points·by smaddrellmander·पिछला माह·0 comments

Are contrastive losses just cross entropy all along?

idlemachines.co.uk
2 points·by smaddrellmander·पिछला माह·0 comments

Every token, everywhere, all at once

idlemachines.co.uk
2 points·by smaddrellmander·2 माह पहले·0 comments

The cut in the Mixture of Experts compute graph

idlemachines.co.uk
1 points·by smaddrellmander·2 माह पहले·0 comments

DeepSeek V4 from the Inside

idlemachines.co.uk
2 points·by smaddrellmander·2 माह पहले·0 comments

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

idlemachines.co.uk
134 points·by smaddrellmander·3 माह पहले·47 comments

Gemma 4 is not your standard transformer

idlemachines.co.uk
2 points·by smaddrellmander·3 माह पहले·0 comments

comments

smaddrellmander
·4 दिन पहले·discuss
Love this! Cute graphics and the way the balls combine is really fun. Great job.
smaddrellmander
·2 माह पहले·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.