vroom vroom @thinkingentity

My fav YouTube channel has now finished, the first year of Cambridge mathematics for free :)

After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x cheaper (w/ output tokens free) • Frontier composable intelligence optimized for decisions AFAICT the shortest path to AI-based economic revolution

Absouloutly fucked this is free.

David Ch @chhddavid

6 days ago

x.com/i/article/2093…

25 72 1K 921K 7K

My list of the best YouTube channels to learn DevOps. 👇

Train your own LLM from scratch! A step-by-step repo that walks you through building and training a transformer model from scratch using PyTorch. From downloading training data all the way to generating text. The architecture is built from the ground up following the original "Attention is All You Need" paper. MLP, single head attention, multi-head attention, transformer blocks, and the full transformer model - all coded and explained with detailed diagrams at each step. Training data comes from The Pile - a diverse 825GB open-source dataset covering books, articles, code, websites, and more. The repo includes scripts to download it, preprocess and tokenize it using tiktoken, store it in HDF5 format, and feed it into training batches. You can train a 13M parameter model on a single Colab T4 GPU. At 13M parameters the model starts generating proper grammar and coherent short sentences. For billion-parameter training you need at least an A100 or RTX 4090. The repo includes a full GPU compatibility table so you know exactly what's possible on your hardware. Includes a complete SFT and RLHF guide as a separate notebook for taking your trained model further. Key capabilities: • End-to-end pipeline: data download → preprocessing → training → text generation • Full transformer implementation from scratch with PyTorch • Trains models from 13M to 2B+ parameters on a single GPU • Training data from The Pile (825GB, 22 diverse datasets) • Tokenization via tiktoken (r50k_base) • SFT and RLHF guide included 100% open source. I've shared the link in the replies!

AI Engineer Complete Resource Kit 2026 (400+ resources): docs.google.com/spreadsheets/d… Like & repost for others!

$41,000,000/month💀 it’s insane how much money survival mobile games make

An absolutely brilliant textbook "Foundations of Large Language Models" by Tong Xiao and Jingbo Zhu (2025) is now in @ChapterPal's collection. This book is a comprehensive, technically grounded treatment of modern generative language models for artificial intelligence researchers, engineers, and advanced students in natural language processing. Assuming a foundational background in deep learning, probability, and standard neural sequence modeling, the book explains the entire lifecycle of foundation models—from raw data pre-training and architectural design to alignment, inference acceleration, and system-level scaling. It's a great in-depth read specifically on Large LMs after my The Hundred-Page Language Models Book that covers neural network and deep learning basics, count-based LMs, RNNs, and transformers. Read the book with an AI tutor: chapterpal.com/ebook/14fa0543… (All books on ChapterPal are free to read with a free account.) The book has 76 beautiful illustrations across 277 pages. Table of contents: Preface Notation 1. Pre-training - 1.1. Pre-training NLP Models * 1.1.1 Unsupervised, Supervised and Self-supervised Pre-training * 1.1.2 Adapting Pre-trained Models - 1.2. Self-supervised Pre-training Tasks * 1.2.1 Decoder-only Pre-training * 1.2.2 Encoder-only Pre-training * 1.2.3 Encoder-Decoder Pre-training * 1.2.4 Comparison of Pre-training Tasks - 1.3. Example: BERT * 1.3.1 The Standard Model * 1.3.2 More Training and Larger Models * 1.3.3 More Efficient Models * 1.3.4 Multi-lingual Models - 1.4. Applying BERT Models - 1.5. Summary - References 2. Generative Models - 2.1. A Brief Introduction to LLMs * 2.1.1 Decoder-only Transformers * 2.1.2 Training LLMs * 2.1.3 Fine-tuning LLMs * 2.1.4 Aligning LLMs with the World * 2.1.5 Prompting LLMs - 2.2. Training at Scale * 2.2.1 Data Preparation * 2.2.2 Model Modifications * 2.2.3 Distributed Training * 2.2.4 Scaling Laws - 2.3. Long Sequence Modeling * 2.3.1 Optimization from HPC Perspectives * 2.3.2 Efficient Architectures * 2.3.3 Cache and Memory * 2.3.4 Sharing across Heads and Layers * 2.3.5 Position Extrapolation and Interpolation * 2.3.6 Remarks - 2.4. Summary - References 3. Prompting - 3.1. General Prompt Design * 3.1.1 Basics * 3.1.2 In-context Learning * 3.1.3 Prompt Engineering Strategies * 3.1.4 More Examples - 3.2. Advanced Prompting Methods * 3.2.1 Chain of Thought * 3.2.2 Problem Decomposition * 3.2.3 Self-refinement * 3.2.4 Ensembling * 3.2.5 RAG and Tool Use - 3.3. Learning to Prompt * 3.3.1 Prompt Optimization * 3.3.2 Soft Prompts * 3.3.3 Prompt Length Reduction - 3.4. Summary - References 4. Alignment - 4.1. An Overview of LLM Alignment - 4.2. Instruction Alignment * 4.2.1 Supervised Fine-tuning * 4.2.2 Fine-tuning Data Acquisition * 4.2.3 Fine-tuning with Less Data * 4.2.4 Instruction Generalization * 4.2.5 Using Weak Models to Improve Strong Models - 4.3. Human Preference Alignment: RLHF * 4.3.1 Basics of Reinforcement Learning * 4.3.2 Training Reward Models * 4.3.3 Training LLMs - 4.4. Improved Human Preference Alignment * 4.4.1 Better Reward Modeling * 4.4.2 Direct Preference Optimization * 4.4.3 Automatic Preference Data Generation * 4.4.4 Step-by-step Alignment * 4.4.5 Inference-time Alignment - 4.5. Summary - References 5. Inference - 5.1. Prefilling and Decoding * 5.1.1 Preliminaries * 5.1.2 A Two-phase Framework * 5.1.3 Decoding Algorithms * 5.1.4 Evaluation Metrics for LLM Inference - 5.2. Efficient Inference Techniques * 5.2.1 More Caching * 5.2.2 Batching * 5.2.3 Parallelization * 5.2.4 Remarks - 5.3. Inference-time Scaling * 5.3.1 Context Scaling * 5.3.2 Search Scaling * 5.3.3 Output Ensembling * 5.3.4 Generating and Verifying Thinking Paths - 5.4. Summary - Appendix - References

Beginner-friendly LLM course exploring foundations, architectures, training, deployment, and current trends: tinyurl.com/vp844fsm v/@Hesamation

A Stanford professor took two average stocks, rebalanced them daily, and turned $100,000 into $7 million without predicting a single price. Bookmark & watch today, no matter what.

x.com/i/article/2090…

Guy lives the most interesting indie career I've ever seen 👏👏👏

Marc Lou @marclou

2 weeks ago

I’ll be paid $103,000 to race so far. I’m going to bed now, let’s see what gets tattooed on my body tomorrow! Auction ends in 6 hours btw.

149 9 682 306K 74

x.com/i/article/2099…

AI/ML Series (Lesson 6/100): RAG projects that actually land interviews. -- Foundation Level -- Document Analysis with LLMs → Process PDFs instantly → Extract key insights → lnkd.in/dvPehYtB First RAG System → Build from scratch → No frameworks needed → lnkd.in/dRq4NnCm IBM RAG Guided → Step by step → Production patterns included → lnkd.in/dgTz_Av6 -- Advanced Techniques -- GraphRAG Pipeline → Knowledge graph retrieval → Smarter context understanding → lnkd.in/dNmynkGZ Multi Document RAG → Query across sources → Unified retrieval logic → lnkd.in/dEj8478y Agentic RAG Pipeline → Autonomous decision making → Tool calling integrated → lnkd.in/gXWsJYXT Real Time Assistant → LangChain powered system → Live data retrieval → lnkd.in/gbHjG7Df AI Research Agent → Automate paper analysis → Smart summarization built-in → lnkd.in/dec__v4e Multimodal RAG System → Text and images → IBM guided tutorial → lnkd.in/d6UwUX3z LangChain RAG Agent → Production ready architecture → Memory and tools → lnkd.in/drdmzwg6 Master these 10 projects. You're building intelligent systems not just writing code. Save for later. Repost ♻️ for AI builders.

Mahesh Nani @maheshnani122

2 weeks ago

AI/ML Series (Lesson 5/100): AI Agent Project Structure 🤖 Building an AI agent is not just about connecting an LLM to a prompt. As the project grows, you need a clean structure so you can add tools, memory, APIs, models, and tests without turning the codebase into a mess.

15 5 49 10K 33

《Build an AI Agent (From Scratch)》：manning.com/books/build-an… Manning的新书，阐述如何在不使用外部框架的情况下，从设计到部署逐步构建一个实验性的Python代理。

so many cool classes coming up in the fall quarter! - Deep Learning Alchemy by @kothasuhas @tatsu_hashimoto @wen_kaiyue : deep-learning-alchemy.github.io - Engineering AI Agents by @Diyi_Yang @michaelryan207 @jyangballin : cs329z.stanford.edu - AI Agents by @gneubig @dan_fried : cmu-agents.com - World Models by @thoma_gu : cis.upenn.edu/~cis6280/ have fun learning my friends

this is pure f*cking treasure how to build your first ai agent (full walkthrough) a year ago this would have saved me two weeks. my first agent would've shipped the same afternoon in the right hands it changes what one person can ship alone:

Mr. Buzzoni @polydao

3 weeks ago

x.com/i/article/2096…

14 87 592 1.3M 2K

Computer scientists discover the power of *closed loop* and *error correction*! I have advocated for many years by now that all intelligent systems would be closed-loop, not open end-to-end. This has been the very basic lesson from Cybernetics (control theory and systems theory), originated more than 80 years ago. This view has been prominently featured in our open-sourced new book about the principles of intelligence: ma-lab-berkeley.github.io/deep-represent…

AYi @AYi_AInotes

2 weeks ago

前 Scale AI 创始人、刚出任 @Meta 首席 AI 官的 @alexandr_wang ，在 YC 现场跟 @garrytan 对谈时抛出这枚深水炸弹，直接把全网的技术管理层给听沉默了。 他说在 Meta 内部，我们已经真实看到了这种情况： 只要设计出正确的智能体循环（Agentic

102 309 1K 404K 2K

this paper is f*cking insane it analyzed 56,000 trading strategies and found something brutal: over 40% looked strong in-sample out-of-sample, the average Sharpe collapsed to basically zero the framework is ruthless: test on unseen data add real costs check regime robustness assume high Sharpe can come from luck the crazy part is that testing 10,000 random strategies can produce a Sharpe above 2.0 purely by chance and after frictions, the median Sharpe in the sample fell from 1.23 to 0.08 most traders search for the strategy with the highest backtest real quants search for the one that still exists after reality touches it bookmark before this thread gets buried

kvro @0xkvro

a month ago

x.com/i/article/2087…

10 42 279 614K 765

Inference roadmap I gotta follow: 1) Watch this course fully : youtube.com/playlist?list=… (Covers everything related to LLM Inference+ Training but on high level) 2) Gonna read this resource: jax-ml.github.io/scaling-book/ ( for deep dive on topics) 3) Read PMPP(CUDA & GPU specific chapters) 4) Blogs and codebase of vLLM , SGlang, llama.cpp 5) Inference Engg by philip book for brush up on the concepts 6) Also these notes which i found randomly on X for brushup: x.com/gauri__gupta/s… Along with it : contributions to the above mentioned repo for understanding depth + talking with folks building in inference here

Gauri Gupta @gauri__gupta

5 months ago

x.com/i/article/2027…

11 94 757 303K 2K