Behnam Amiri

Perceptron lover

[Behnam Amiri @TensorDude]

@kooshiar Just dropped my two cents in there.

https://t.co/aQaq3FApp9

[Behnam Amiri @TensorDude]

@realDonaldTrump Thank you, Mr. President!

[Behnam Amiri @TensorDude]

Launching DriftQ 🚀

A durable message broker + workflow foundation for reliable backend + AI workflows — without heavy infra.

GitHub: https://t.co/vB1G20PjPe
Website: https://t.co/krxobZBCOG

Excited to see what you build.

#OpenSource #Golang #AI #WorkflowOrchestration

[SKG @sonukg4india]

#Mathexplained v40

[Fernando @Franc0Fernand0]

One of the best math books I've ever read:

MIT's "Mathematics for Computer Science"

Its writing style is brilliant, and it covers everything:

- Linear algebra
- Series
- Logic
- Probability
- Number theory
- Graphs

You can find the PDF here:

https://t.co/iQvaflkDPD

[PyTorch @PyTorch]

Need to accelerate Large-Scale Mixture of Experts Training?

With @nvidia NeMo Automodel, an open source library within NVIDIA NeMo framework, developers can now train large-scale MoE models directly in PyTorch using the same familiar tools they already know.

Learn how to make MoE training of massive models simple and efficient by reading NVIDIA’s developer blog:
📎 https://t.co/xGnx95jY8y

#PyTorch #MoE #OpenSourceAI

[PyTorch @PyTorch]

With its v5 release, Transformers is going all in on #PyTorch. Transformers acts as a source of truth and foundation for modeling across the field; we've been working with the team to ensure good performance across the stack. We're excited to continue pushing for this in the future across training, inference, and deployment. - @matthew_d_white Executive Director, @PyTorch Foundation / GM of AI, @linuxfoundation

[Elon Musk @elonmusk]

https://t.co/op5s4ZikGJ is fully open source, so anyone can use it for anything at no cost

[PyTorch @PyTorch]

Post-training, sometimes called alignment, enables #LLMs to plan, reason, and interact, which pre-training alone doesn't provide.

Our latest blog is a primer on post-training for engineers new to LLM modeling, covering SFT, RLHF, DPO, etc.

🔗 https://t.co/tOosAXwCMD

#PyTorch

[Jeremy Howard @jeremyphoward]

LLMs have achieved PhD level intelligence

[PyTorch @PyTorch]

Introducing #ZenFlow: No Compromising Speed for #LLM Training w/ Offloading
5× faster LLM training with offloading
85% less GPU stalls
2× lower I/O overhead
🚀 Blog: https://t.co/emUxxDQoGI
🚀 Try ZenFlow and experience 5× faster training with offloading: https://t.co/ppcoI4Af7V

[Philosophy Of Physics @PhilosophyOfPhy]

Mathematical Thinking ;

"For People Who Hate Math"

- by Albert Rutherford

[Behnam Amiri @TensorDude]

@Blender

[Blender 🔶 @Blender]

Blender Foundation and the online developer community proudly present Blender 4.5 LTS!

Vulkan, faster EEVEE, improved compositor, Geometry Nodes, nearly 500 bugs fixed, and so, so much more.

👉Release notes: https://t.co/mKRx7LI3Gz

📺Video recap: https://t.co/0olWI8jCMo #b3d

[John Preskill @preskill]

Mathematician @evamirandag expounds on undecidability in fluid mechanics. This is fun: It's about rubber duckies drifting in the ocean.
https://t.co/ZKWDSuIwQH

[Massimo @Rainmaker1973]

Scientists believe the Milky Way is flying through space at 600 kilometers per second while also wobbling slightly, as if it’s flipping its wings through the cosmos

[Physics In History @PhysInHistory]

Everything we call real is made of things that cannot be regarded as real.

If quantum mechanics hasn't profoundly shocked you, you haven't understood it yet.

- Niels Bohr

[Python Software Foundation @ThePSF]

On the PSF Blog: A summary of the "An Uncontentious Talk about Contention" by Mark Shannon during the #Python Language Summit at #PyConUS 2025
https://t.co/ZWaM9jxEFw

[Dan Kornas @DanKornas]

👉 Introduction to Machine Learning

The course serves as a basic introduction to machine learning and covers key concepts

🔗 https://t.co/rNXd8QSOfK

[ア @yuruyurau]

a=(x,y,d=mag(k=4*cos(x/29),e=y/7-13))=>point((q=3*sin(atan2(k,e)*19)+sin(y/19)*k*(9+2*sin(e*9-d*3+t/4)))+60*cos(c=d-t/8)+200,q*sin(c)+d*39-195)
t=0,draw=$=>{t||createCanvas(w=400,w);background(9).stroke(w,146);for(t+=PI/15,i=1e4;i--;)a(i,i/235)}//#つぶやきProcessing