Tag: AI

Wanted to understand how the core transformer papers actually connect at the concept level - not just "Paper B cites Paper A" but what specific methods, systems, and ideas flow between them. I ran 12 foundational papers (Attention Is All You Need, BERT, GPT-2/3, Scaling Laws, ViT, LoRA, Chain-of-Thought, FlashAttention, InstructGPT, LLaMA, DPO) through https://github.com/juanceresa/sift-kg (open-source CLI) - point it at a folder of documents + any LLM, get a knowledge graph. 435-entity knowledge graph with 593 relationships for ~$0.72 in API calls (gpt 4o-mini). Graph: https://juanceresa.github.io/sift-kg/transformers/graph.html - interactive and runs in browser. Some interesting structural patterns: - GPT-2 is the most connected node - it's the hub everything flows through. BERT extends ...

"By applying new methods of machine learning to quantum chemistry research, Heidelberg University scientists have made significant strides in computational chemistry. They have achieved a major breakthrough toward solving a decades-old dilemma in quantum chemistry: the precise and stable calculation of molecular energies and electron densities with a so-called orbital-free approach, which uses considerably less computational power and therefore permits calculations for very large molecules. [...] How electrons are distributed in a molecule determines its chemical properties—from its stability and reactivity to its biological effect. Reliably calculating this electron distribution and the resulting energy is one of the central functions of quantum chemistry. These calculations form th...