Yacine

heeeey thanks buddy for the shout out

That’s how I start all my YouTube tutorial about the latest deep learning architecture.

Started coding a while game with the kids, whew this is fun!

I just asked ChatGPT to help me set up the boilerplate for a Python script that make use of their API.

1. Secret is pasted straight into file, no environment management.
2. The code is for a deprecated API.

What a vibe.

2025 will be the year of linear attention, I feel it.

That just happened to me with tiling for linear attention. God I feel free now. 🥲

There is an exhilarating feeling in finally understand a whole line of research after a few weeks of study.

It’s like a flash of every paper, formula and code seen that just come flooding all at once in its correct form.

Most foundational models use softmax attention, which scales quadratically with input length—a major bottleneck.

Linear attention has existed since 2020, yet large-scale models rarely use it. Why?

minimax-01 finally makes linear attention work at scale. Deep dive here: 📌 youtu.be/iRuvGU-Sk3c

Linear Algebra Study Session - Sarrus Rule and Laplace Expansion YouTube video by Deep Learning with Yacine

The next live is going to be about Eigenvectors and Eigenvalues!

You can catch this Sunday live over here about the determinants:
📌 youtube.com/live/ligNtLS...

Keep studying and growing folks!

I'm back for the weekly deep-learning study session! ✨

Sorry for the month break, was a bit overwhelmed with lots of things at work.

I'll try to move around the schedule a bit so that more people in different time zones can attend.

📸 PS: I gave a talk at a conference in February!

What’s you three best ones?

YouTube video by Deep Learning with Yacine Introduction to AI Agents - Theory and Code

Lots of confusion out there about what AI Engineering is about.

What's an agent, what's a workflow, what's an agentic system, etc.

I made this tutorial on the topic packed with information from the latest research from HuggingFace.

Check it out over here:
youtu.be/UMYKjT9exb4

Enjoy! 🌹

There will be massive shortage of senior dev in 1-3 year time.

Very hard for junior to get hired and very hard for them to understand deeply what is going on in their system.

This is the kind of research we need more of:

The state of AI/consciousness discourse:

They are really easy to anthropomorphize with the CoT being visible.

You show that trace to any non-tech folks and they now believe AGI has come.

Screenshot of a twitter post showing that the latest openAI commercial model is better than previous models at doing arithmetic but still cannot reliably produce the correct answer of multiplication problems with values greater than 11 x 11. It's supposed to be impressive I think

you fucked up a perfectly good computer is what you did. look at it. it's got innumeracy

Wouldn’t it be funny that we never reach AGI because of short term incentive to keep going with Transformers.

Then we patch the whole thing left and right to keep the illusion of general intelligence with massive injection of capital.

Literally yeeting the AI field in a local minima and digging.

Might be slightly off topic here, but DeepSeek R1 when trained to do reasoning use multiple language in its chain of thought.

Actively repressing the multi language reasoning lead to worse result in the benchmarks.

This is so well put, must read!

Open AI is getting absolutely cooker right now.
Crazy how we went from the darling of AI to a company researchers loathe.

not a good vibe.

Yeah Dark Soul is much more tightly crafted.

Best of luck!

I mean, if you studied software engineering prior to your professional 5+ years you meet the criteria.

Hey, don’t forget to take a lot of vitamin D.

I got Seasonal Affective Disorder that kicks in every winter like clockwork, but with enough Vitamin D it’s MUCH more manageable.

Their play would be so much stronger if they embraced the openness aspect and focused on being that base AI layer that everyone can trust.

Which this role is currently being owned by Meta.

Provide the infra, release the research, energize the community and push for regulation if needs be.

The one thing I dislike about current v. of OpenAI is how surface level they are in their research coms.

They are hinting big breakthrough, but man look at the landscape.

Every competitors around is stacked with billions and PhD.

Whatever they are trying to win, won’t be achieved by secrecy.

how i'd learn machine learning in 2025 if i had to start from scratch:

1. find a log that i initially planned to turn into a table leg
2. make it into a puppet that can walk and talk
3. have the puppet, through a series of adventures, turn into a real boy and realize the true value of friendship

Which part you feel are missing?

In my view its missing the melancholy, it’s a bit more upbeat.