Stoney
@Castillonis
Followers
161
Following
5K
Media
92
Statuses
2K
RT @bryan_johnson: HBOT and sauna boosted VEGF 19x in 9 months. this hormone builds blood vessels . allowing more oxygen and nutrients t….
0
64
0
RT @akshay_pachaar: ML researchers just built a new ensemble technique. It even outperforms XGBoost, CatBoost, and LightGBM. Here's a com….
0
182
0
RT @jasonbosco: I’m going to show you how *incredibly easy* it is to add some AI-magic to the search bar in your sites & apps in 2025 using….
0
348
0
RT @bryan_johnson: 15 sessions of sauna dramatically reduced toxins in my body. 65% drop in 2,4-D. 100% drop in MEP. 15% drop in MBP. ….
0
476
0
RT @gabriberton: Every single VLM/MLLM paper in the last few months uses Qwen as LLM. Not Gemma, not Llama, not DeepSeek. But Qwen. Every s….
0
39
0
RT @thorstenball: Finally did it. I wrote down how to build a code-editing agent. In 315 lines of code. And yes, it works. Very well. The….
0
629
0
RT @rasbt: Coded Llama 3.2 model from scratch and shared it on the HF Hub. Why? I think 1B & 3B models are great for experimentation, and I….
0
283
0
RT @sewoong79: We are releasing OpenDeepSearch (ODS), an open-source search agent that works with any LLM. When paired with DeepSeek-R1, OD….
0
311
0
RT @CodeByPoonam: RIP Sora. China just dropped another open-source model: VACE, their Video generator. 7 WILD examples so far: https://t.co….
0
233
0
RT @reach_vb: Alright, this pretty WILD! Orpheus 3B - high quality, emotive Text to Speech - Apache 2.0 licensed! 🔥. > Zero shot voice clon….
0
141
0
RT @levelsio: I'm organizing the. 🌟 2025 Vibe Coding Game Jam. Deadline to enter: 25 March 2025, so you have 7 days. - anyone can enter wit….
0
451
0
RT @bryan_johnson: 8/ Don't Die Certified Clinics - coming soon . Wanting to do HBOT and but don't know where? . Soon, you will be able to….
0
16
0
RT @bryan_johnson: HBOT ranks as one of the highest value health therapies I’ve done. Results from 60 sessions:. wiped out all systematic….
0
317
0
RT @maximelabonne: I partnered with @huggingface and @ben_burtenshaw to teach people how to fine-tune LLMs with GRPO. In this notebook,….
0
385
0
RT @burkov: This is my minimalist implementation from scratch of the GRPO reinforcement learning algorithm used to train DeepSeek R1. Here'….
0
124
0
RT @natolambert: Since everyone wants to learn RL for language models now post DeepSeek, reminder that I've been working on this book quiet….
0
167
0
RT @karpathy: We have to take the LLMs to school. When you open any textbook, you'll see three major types of information:. 1. Background….
0
2K
0
RT @rasbt: But before I get to the reasoning model space. if you are looking to do some focused offline reading this weekend, I just re-c….
sebastianraschka.com
This article covers 12 influential AI research papers of 2024, ranging from mixture-of-experts models to new LLM scaling laws for precision.
0
165
0