RRounak Show·2d agoInside Attention: Why Softmax Sits Between QKᵀ and VWhen I first learned self-attention, the formula looked straightforward: $$\operatorname{Attention}(Q,K,V)=\operatorname{softmax}\left(\frac{QK^\top}{\sqrt{d_k}}+M\right)V$$ But one question bothered6 min read·rounakshow.hashnode.dev
NNishanthan Karunakaran·Oct 15Understanding Transformer: The Architecture Behind Modern AIWhat Is a Transformer? A Transformer is a neural network architecture introduced by Google researchers in 2017 in the paper Attention Is All You Need. It uses attention mechanisms to help the model le6 min read·nishanthan.hashnode.dev1
EEkansh Nangia·Sep 17Introduction To Mechanistic InterpretabilityHow do LLMs actually work? Explore mechanistic interpretability, AI epistemology, and why probing neural networks cannot crack the AI black box.18 min read·ekanshn.hashnode.dev
SSunney Sood·Sep 11How Large Language Models Actually Work: From Your Prompt to Every Word They WriteA complete, plain-English mental model — from tokens to attention to the exact moment ChatGPT picks its next word. When you type a question into ChatGPT and an answer appears a few seconds later, it26 min read·sunneysood.hashnode.dev
RRahul Sai Indeevar V·Sep 7Advanced Transformers: Positional Encodings (RoPE) & Efficient Attention Mechanisms (KV Caching, MQA, GQA, MLA)In modern Large Language Model (LLM) architectures, two foundational engineering bottlenecks dictate model scalability and inference latency: Representing Order: How self-attention mechanisms—which a15 min read·rahul-ai.hashnode.dev13A
RRahul Sai Indeevar V·Sep 2Classical NLP to Attention: Guide to Sequence ModelingNatural Language Processing (NLP) has undergone a massive paradigm shift over the past decade. We have moved from handcrafted rule-based systems and statistical frequencies to complex sequential archi11 min read·rahul-ai.hashnode.dev1
VVijay Ram Enaganti·Aug 31Reproducing Sequential Attention(and finding out where my reproduction disagrees with Google's)9 min read·vijay-ram.hashnode.dev1
VViv Chaudhary·Aug 22Five Mental Models That Make Modern AI Click Tokens, context windows, embeddings, attention, and scale - the five ideas that stop new model releases from feeling like starting over12 min read·truenorthbits.hashnode.dev
AAkash·Aug 5Abstractive Text Summarization with Attention Mechanism: Seq2Seq Model for Academic PapersBuild an end-to-end abstractive text summarization system using Seq2Seq LSTM encoder-decoder with attention mechanism to generate concise summaries.7 min read·akashbuilds.hashnode.dev
PPiyush Jadhav·Aug 3Attention Mechanism in Deep Learning: The Foundation of TransformersLearn how Attention Mechanisms enable AI models to focus on the most relevant information, improving accuracy and powering modern applications like ChatGPT, BERT, and machine translation.4 min read·attentionmechanism.hashnode.dev
