t_harshv's profile picture. Random Observations 🧐. On the pursuit of one-vs-all learning algorithm 👨‍💻. #ML #DL #startups

Harsh Vardhan

@t_harshv

Random Observations 🧐. On the pursuit of one-vs-all learning algorithm 👨‍💻. #ML #DL #startups

Fissato

Hi! This is my attempt to demystify the minutae of Machine Learning and Deep Learning. The goal is for the information to be complete and intuitive. #MachineLearning #DeepLearning #MachineLearningwithHarsh #YouTube youtube.com/channel/UC6sjv…


Real Madrid look like a team with no map, no compass, no leader. Xabi needs to figure out his tactics soon, and the players need to stop being headless in the final third. At the moment, the squad is out there doing cardio, not football. #RealMadrid #RealMadridCelta


Repost di Harsh Vardhan

This video from 2003 proves why NVIDIA eventually became the most valuable company in the world:


Repost di Harsh Vardhan

🚨: The Human Brain Builds Structures in 11 Dimensions, Discover Scientists Your brain might be doing something far more complex than anyone imagined. Scientists from the Blue Brain Project in Switzerland have discovered that the human brain builds intricate structures capable…

forallcurious's tweet image. 🚨: The Human Brain Builds Structures in 11 Dimensions, Discover Scientists

Your brain might be doing something far more complex than anyone imagined. Scientists from the Blue Brain Project in Switzerland have discovered that the human brain builds intricate structures capable…

Repost di Harsh Vardhan

Last night I taught nanochat d32 how to count 'r' in strawberry (or similar variations). I thought this would be a good/fun example of how to add capabilities to nanochat and I wrote up a full guide here: github.com/karpathy/nanoc… This is done via a new synthetic task…

karpathy's tweet image. Last night I taught nanochat d32 how to count 'r' in strawberry (or similar variations). I thought this would be a good/fun example of how to add capabilities to nanochat and I wrote up a full guide here:
github.com/karpathy/nanoc…

This is done via a new synthetic task…

Repost di Harsh Vardhan

Everyone wants to get into robotics. No one knows where to start. LeRobot's Francesco just dropped a 70-page crash course that takes you from zero to cutting-edge: - RL sim/real - ACT, Diffusion policies - VLAs, SmolVLA, Pi-0 Absolute gold if you want to catch up fast.

A comprehensive, hands-on tutorial on the most recent advancements in robotics 🤟 ...with self-contained explanations of modern techniques for end-to-end robot learning & ready-to-use code examples using @LeRobotHF and @huggingface. Now available everywhere! 🤗

_fracapuano's tweet image. A comprehensive, hands-on tutorial on the most recent advancements in robotics 🤟

...with self-contained explanations of modern techniques for end-to-end robot learning & ready-to-use code examples using @LeRobotHF and @huggingface. Now available everywhere! 🤗


Repost di Harsh Vardhan

Excited to release new repo: nanochat! (it's among the most unhinged I've written). Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,…

karpathy's tweet image. Excited to release new repo: nanochat!
(it's among the most unhinged I've written).

Unlike my earlier similar repo nanoGPT which only covered pretraining, nanochat is a minimal, from scratch, full-stack training/inference pipeline of a simple ChatGPT clone in a single,…

Repost di Harsh Vardhan

Physics.


Repost di Harsh Vardhan

Seeking students & open-source contributors to join some ML-for-science projects at @huggingface. If you're curious about ML × biology or ML × materials science, this could be a great way to learn + contribute. I can offer Pro subs, support, and (for longer-term work)…


Repost di Harsh Vardhan

Singapore's AI-powered legal research platform, #Lawnet, is a game-changer. Its Gen AI features allow legal professionals to conduct research more efficiently by asking questions in natural language and getting instant, sourced answers from case law and legislation. With over 5…


Repost di Harsh Vardhan

We’re open-sourcing everything. All the projects built during the Nano Banana Hackathon are now released as open-source. Since AI Studio supports remixing, you can easily adapt and reuse them. They may not have been huge projects, but it was a great opportunity to truly…


Repost di Harsh Vardhan

Lack of growth is just lack of courage to take real responsibilities.


Repost di Harsh Vardhan

This former Google exec just came out with a cruel prediction: "Unless you're in the top 0.1%, you're a peasant. There is no middle class." He says AI will make this reality by 2027. And his reasoning will keep you up at night... Here's what he told Steven Bartlett: 🧵

anarchy_build's tweet image. This former Google exec just came out with a cruel prediction:

"Unless you're in the top 0.1%, you're a peasant. There is no middle class."

He says AI will make this reality by 2027.

And his reasoning will keep you up at night...

Here's what he told Steven Bartlett: 🧵

Repost di Harsh Vardhan

Just created a GitHub repo to push football analytics experiments for anyone interested: analysts, scouts, developers who love the intersection between programming + data + football. Check the first tutorial in notebooks/match_dashboard_template.ipynb github.com/ricardoheredia…


Repost di Harsh Vardhan

🚀 Big news in healthcare AI! I'm thrilled to announce the launch of OpenMed on @huggingface, releasing 380+ state-of-the-art medical NER models for free under Apache 2.0. And this is just the beginning! 🧵

MaziyarPanahi's tweet image. 🚀 Big news in healthcare AI! I'm thrilled to announce the launch of OpenMed on @huggingface, releasing 380+ state-of-the-art medical NER models for free under Apache 2.0. 

And this is just the beginning! 🧵

Repost di Harsh Vardhan

Insane. @Stanford just dropped Co-STORM, an AI tool that writes research papers like a PhD! 🤯 - 99% factual accuracy - Cited sources (with references) - Completely free Type a topic → it reads the web → you get a polished, cited PDF report. repo and free app in 🧵↓


Repost di Harsh Vardhan

In a new study, MIT researchers have successfully modeled how people deploy different decision-making strategies to solve a complicated task — offering insights for building machines that think more like us. news.mit.edu/2025/how-brain…


Mbappé can never play as a striker. Let’s stop pretending that experiment ever worked. #RealMadridVsArsenal #RealMadrid #Mbappe


#RMAFCB #SupercopaDeEspaña This loss falls squarely on Ancelotti. What "learnings" was he referring to? Total rubbish!! 🤷🏻🤦🏻


United States Tendenze

Loading...

Something went wrong.


Something went wrong.