learning with yacine

how to stop having FOMO as a curious engineer: hold a thread

little worthless advice to learn passionately without boxing yourself

Nov 11 • 

Yacine Mahdid

14

September 2025

Hierarchical Reasoning Model assembly manual for toddlers

fun time for the whole family.

Sep 9 • 

Yacine Mahdid

7

2

1

August 2025

get your A in college and stop wasting your life

it's not complicated.

Aug 25 • 

Yacine Mahdid

4

how to stop feeling lost in tech: the wafflehouse method

you need to sit for this one for 48h

Aug 20 • 

Yacine Mahdid

102

14

10

muon optimizer explained to a toddler

there's no way you won't get it

Aug 19 • 

Yacine Mahdid

16

1

May 2025

Next Frontier for LLM is Quality Long Context

Which is much harder than you think.

May 26 • 

Yacine Mahdid

2

4

April 2025

How Minimax-01 Achieves 1M Token Context Length with Linear Attention (MIT)

I've dig into the internal of an MIT licensed MoE system that makes use of Linear Attention (Lightning Attention) to extend it's context length to 1M…

Apr 1 • 

Yacine Mahdid

2

March 2025

You shouldn't build fully autonomous agent.

That's a big no no.

Mar 10 • 

Yacine Mahdid

2

February 2025

AI Engineering is Stochastic Software Development

It's not related to ML.

Feb 21 • 

Yacine Mahdid

7

1

Learning to program? In 2025? Why??

AI can do it for you!

Feb 19 • 

Yacine Mahdid

1

2

Going too deep in R1...

Why Deepseek R1 KL divergence looks like that?

Feb 17 • 

Yacine Mahdid

3

The TLDR on DeepSeek R1

Simpler than I originally thought!

Feb 3 • 

Yacine Mahdid

5