llm_enjoyer's banner

llm_enjoyer

@LLMenjoyer • 1,415 subscribers

火を求める者、王たらんと欲する者よ

Shorts

u js trained on test bro, it's not that deep

u js trained on test bro, it's not that deep

210,929 просмотров

...count ur parameters! which lab are u?

...count ur parameters! which lab are u?

207,198 просмотров

reading the deepseek v4 report be like

reading the deepseek v4 report be like

76,687 просмотров

bro the NEURAL CIRCUITS bro!! the SPARSE AUTOENCODERS...!

bro the NEURAL CIRCUITS bro!! the SPARSE AUTOENCODERS...!

48,429 просмотров

as a researcher, it's important to not just solve any problems, but solve the right problems.

as a researcher, it's important to not just solve any problems, but solve the right problems.

41,316 просмотров

video of my training runs

video of my training runs

29,959 просмотров

comparing their benchmark scores is fucking nuts bro

comparing their benchmark scores is fucking nuts bro

33,103 просмотров

what's actually happening when u autokernel:

what's actually happening when u autokernel:

17,241 просмотров

when people at my company ask how I'm hitting all these 16 node jobs

when people at my company ask how I'm hitting all these 16 node jobs

12,444 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

video of how all the hacks in deepseek-v4 tech report came to be

video of how all the hacks in deepseek-v4 tech report came to be

72,104 просмотров • 3 месяцев назад

how it must feel like to be cluster manager for a research company rn

how it must feel like to be cluster manager for a research company rn

41,811 просмотров • 6 месяцев назад

what actually happens wen u loop

what actually happens wen u loop

20,823 просмотров • 3 месяцев назад

pro tip: scale is all u need, actually

pro tip: scale is all u need, actually

15,994 просмотров • 5 месяцев назад

latent moe, jianlin su balancer, mamba 3, attention residuals, 500 hparam changes... when do we cross the line from "yolo run" to "schizo run"?

latent moe, jianlin su balancer, mamba 3, attention residuals, 500 hparam changes... when do we cross the line from "yolo run" to "schizo run"?

13,555 просмотров • 5 месяцев назад

Больше нет контента для загрузки