⚙️ Transformers - aibrain0x01 · Scour

MiniGPT: Rebuilding GPT from First Principles 📝LLMs

How LLM Inference Works 📝LLMs

arpitbhayani.me·6d·Hacker News

KV Cache and Flash Attention with interactive diagrams 🧠Neuromorphic Computing

kvcache.cobanov.dev·10h·Hacker News

HSTU: How Meta Built a Trillion-Parameter Recommender That Actually Scales 📝LLMs

·2d

ViT Overfits Small Datasets: When CNNs Win by 18% mAP 👁️Computer Vision

tildalice.io·5d

Running PyTorch Models on Apple Silicon GPUs with the ExecuTorch MLX Delegate ⚙️MLOps

pytorch.org·2d·Hacker News

Vision-Language-Action Models Arrive 🧠Neuromorphic Computing

semiengineering.com·6d

I ditched Copilot on VS Code for this free extension, and it's miles ahead ⚙️MLOps

xda-developers.com·19h

Replicability of unsupervised deep learning derived image phenotypes 🎨GANs

biorxiv.org·9h

Less-relevant results

Why does off-model SFT degrade capabilities? 📝LLMs

lesswrong.com·4h

A primer on how large language model works 📝LLMs

mayijie.substack.com·4d·Substack

Informatica Deepens Strategic Partnership with Google Cloud, Bringing Headless Data Management and CLAIRE® Conversational AI to the Enterprise 📱Edge AI

salesforce.com·16h

The Future of Artificial Intelligence in Technology ✨Generative AI

You can put a Softmax in front of CrossEntropyLoss. PyTorch won’t stop you. Here are 16 other architecture bugs it won’t catch. ⚙️MLOps

gaox.substack.com·3d·Substack

Don’t trust GPT for stock advice, this $55 lifetime tool actually knows what it’s doing 🎨GANs

pcworld.com·21h

Imagining AccessibilityGPT ✨Generative AI

evantravers.com·1d

GPT-5.5 in Ghostreader, Logos highlight imports 🔍RAG

wiseup.readwise.io·5h

Show HN: QuiteGPT – makes GPT response shorter 📝LLMs

quiet-gpt.craftgarden.io·52m·Hacker News

Benchmarking Subquadratic's latest model and SSA Kernel 📝LLMs

appen.com·6d·Hacker News

Créer des chatbots e-commerce propulsés par GPT : ce qui fonctionne vraiment 📝LLMs

yourgpt.ai·1d·DEV

Log in to enable infinite scrolling