https://abhir.ai/tags/learning/ Recent content in Learning on Abhinav Rai Hugo en-us Fri, 06 Mar 2026 00:00:00 +0000 https://abhir.ai/posts/llm-foundations-1/ Fri, 06 Mar 2026 00:00:00 +0000 https://abhir.ai/posts/llm-foundations-1/ <h1 id="what-are-large-language-models">What Are Large Language Models</h1> <h2 id="11-large-language-model">1.1 Large Language Model</h2> <p>An LLM is a neural network trained on massive text datasets to predict the next token in a sequence. Through this simple objective, the model learns grammar, facts, reasoning patterns, and even code.</p> <p>Large Language Models (LLMs) represent a fundamental shift in how machines process and generate human language.</p> <h3 id="111-two-families-of-language-models">1.1.1 Two Families of Language Models</h3> <h4 id="1111-generative-models">1.1.1.1 Generative Models</h4> <p>Produce text outputs (GPT-4, Claude, Llama). Trained to predict the next token autoregressively.</p> https://abhir.ai/posts/on-learning-in-public/ Wed, 04 Mar 2026 00:00:00 +0000 https://abhir.ai/posts/on-learning-in-public/ <p>There&rsquo;s an idea I keep coming back to: the best way to learn something is to explain it.</p> <p>Not to an audience. Not for clout. Just&hellip; explain it. Write it down. Force yourself through the parts where you wave your hands and say &ldquo;and then it kind of works.&rdquo; Those hand-wavy parts are exactly where understanding breaks down.</p> <h2 id="why-write-at-all">Why write at all?</h2> <p>Most of what I read online disappears from my mind within a week. Writing forces me to engage with ideas at a deeper level. When I write about something, I have to:</p>