| # | Tweet | Community | Topic | Views ▼ | Ratio | Engagement | Posted |
|---|---|---|---|---|---|---|---|
| 1 | [video] Hey everyone!
Finally, I, with Claude, was able to make simple, educational and interactive playground for RL come to life!
This is the first step towards a interactive learning website I wanted to have when I first started with RL, and here I think I'll be bale to make it | Machine Learning | — | 12.7K | 4.1x | 31 | Jun 28 |
| 2 | [image] Distributed Training and Inference both involves having a fundamental understanding of how distributed systems work in general
But that’s boring!
We want to read what’s just needed and quickly get started with applications and that’s what exactly what I have for you all today | Machine Learning | — | 933 | 0.3x | 29 | Sep 21 |
| 3 | [image] Finally, all the evaluations of the 13 models (open + closed weights - locally deployed/ API based) has been completed!
Everyday, you'll be seeing how the evaluation worked and the performance of the models on real-life resembled on a real android device - Oneplus 10r 5G
Lets | Machine Learning | — | 902 | 0.3x | 18 | Sep 26 |
| 4 | [video] Releasing Live Task Trajectories on AndroidLife!
Performing a task, what does an agent actually go through? What reasoning? What thoughts?
This features allows to see the end-to-end trace of every 'tap' an agent (LLM) makes on a phone to do the task
Checkout it out now and | Machine Learning | — | 585 | 0.2x | 8 | Sep 29 |
| 5 | [text] On an 8GB Jetson, SmolLM2-135M came out around 165 tok/s and 29.6 tok/J at 25W.
That’s the kind of number I wanted a public board for small open models, same GGUFs, llama.cpp vs Ollama, power modes locked, heat logged.
Writeup on the problem, the protocol, and what’s live and | x/LocalLLaMA | — | 367 | 0.1x | 7 | Sep 16 |
