§6 · Learn · from Outcome School
Outcome School, the AI shelf.
Every AI and machine-learning post by Amit Shekhar at outcomeschool.com, brought in each night — with your reading tracked, search inside every article, a tutor that has read the post, and recall cards so it stays learned.
Last imported 19 Sep 2026, 03:30 CT · posts belong to Outcome School; this shelf links to them and helps you keep what you read · your recall deck
141 shown · you have read 0 of 141
2026-09-19How do Top-k and Top-p Sampling work?How Top-k and Top-p Sampling work, the two most common ways an LLM decides which word to write next when it is replying to us. We will also see how an LLM picks one token at a time, why always picking the best token gives boring text, why picking from every token gives silly text, how Top-k keeps a fixed number of tokens, how Top-p keeps tokens based on their total probability, how both of them work with temperature, and when to use which one.18 min2026-09-17Jev and System One Models ExplainedJev and System One Models, a new kind of AI model that does not write text at all but only makes fast decisions that our software can use directly. We will also see what System One and System Two thinking mean, why using a normal LLM for small decisions is slow and unreliable, how Jev answers many questions in a single pass instead of one word at a time, what a typed answer is, how the probability attached to every answer is made honest, why Jev cannot hallucinate, and where it works well and where it fails.19 min2026-09-16Design a Real-Time Voice AI AgentHow to design a Real-Time Voice AI Agent, a system that listens to a person speaking, understands what they said, thinks about it, takes actions if needed, and talks back in a natural human-like voice, all within a fraction of a second. We will also see why voice is much harder than a text chatbot, the two big ways to build it (the cascaded pipeline of Speech-to-Text, LLM, and Text-to-Speech versus the end-to-end Speech-to-Speech model), how the agent knows when the user has stopped talking, how we handle interruptions, how tools and memory fit in, how we scale it to thousands of calls, the edge cases that break a voice agent in production, the pros and cons of every approach, and when to use which one.63 min2026-09-15How does Temperature control LLM output?How Temperature controls LLM output, the single number that decides whether an AI model gives us a safe and predictable answer or a creative and surprising one. We will also see how an LLM picks one token at a time, how it gives a score to every possible next token, how those scores become probabilities, how Temperature quietly changes those probabilities before the pick happens, what happens at low, high, and zero Temperature, why it is called Temperature, and when to use which value based on our use case.15 min2026-09-15What is Recursive Self-Improvement (RSI)?Recursive Self-Improvement (RSI), the idea of an AI system that makes itself smarter, and then uses that new smartness to make itself even smarter, again and again. We will also see why it matters, how an AI gets better today, how the self-improvement loop works step by step, a simple example with numbers, what already exists in the real world today, why people talk about an intelligence explosion, where it works well and where it fails, and why keeping humans in the loop is very important.22 min2026-09-13N-gram Speculation in LLMsN-gram Speculation in LLMs, a simple trick that makes a language model write its answer faster by guessing the next few words from the text it has already seen. We will also see how an LLM writes one token at a time, why that is slow, what Speculative Decoding is, what an n-gram is, how N-gram Speculation guesses the next tokens by looking up the prompt, how the model verifies those guesses without changing the final answer, and where it works well and where it fails.19 min2026-09-13Prefill-Decode DisaggregationPrefill-Decode Disaggregation, a way of running a large language model where the reading of the prompt and the writing of the answer happen on separate machines. We will also see how an LLM answers a request in two phases, what the KV Cache is, why the two phases need different things from the hardware, what goes wrong when both run on the same machine, how disaggregation solves it step by step, its advantages and disadvantages, and where it works well and where it is overkill.20 min2026-09-12KV Cache CompressionKV Cache Compression, the set of techniques that shrink the memory an AI model uses to remember the conversation while it is writing its reply. We will also see how an LLM writes one token at a time, what the KV Cache is and why we need it, why this cache becomes so huge, how quantization stores the same memory in fewer bits, how we can throw away the tokens that do not matter, how sharing across attention heads reduces the cache, how the cache can be squeezed into a small hidden vector, and when to use which one.20 min2026-09-10Chunking Strategies for RAGChunking Strategies for RAG, the art of cutting a big document into smaller pieces so that an AI system can find the right piece at the right time. We will also see what RAG is, why chunking is needed at all, what happens when we chunk badly, the most useful chunking strategies one by one, how to pick the chunk size and the overlap, and where each strategy works well and where it fails.30 min2026-09-10Vectorless RAGVectorless RAG, a way of answering questions from our own documents without converting those documents into numbers and without using any vector database. We will also see how the normal RAG works, why the vector part creates problems, how a Vectorless RAG system reads a document the way a human reads a book, how the tree structure and the search happen step by step, what the advantages and disadvantages are, and when to use which one.19 min2026-09-05How do Attention Sinks work?How attention sinks work in Large Language Models. We will also see why streaming long conversations becomes a problem, why the first tokens become a sink that the naive fix breaks, and how StreamingLLM uses attention sinks in the real world to keep models running.14 min2026-09-05How does Sliding Window Attention work?How sliding window attention works. We will also see why normal attention becomes slow and expensive for long text, and how sliding window attention comes to the rescue.13 min2026-09-04How does TensorRT-LLM work?How TensorRT-LLM works, NVIDIA's own engine that squeezes the highest possible speed out of an NVIDIA GPU when it runs a large language model. We will also see what inference means, what a GPU kernel is, why a normal model run wastes a lot of the GPU's time, how TensorRT-LLM prepares the model ahead of time instead of figuring things out on the fly, how kernel fusion, quantization, the paged KV cache, in-flight batching, CUDA graphs, and speculative decoding each add speed, how one model is spread across many GPUs, and where it works well and where it fails.45 min2026-09-03How does an LPU work?How an LPU works, the chip that was built for one single job, running a large language model and printing words on our screen as fast as possible. We will also see what an LPU actually is, how a language model writes text one token at a time, why memory and not math is the real bottleneck, how an LPU keeps the model right next to the compute, how the compiler plans every single cycle in advance, how hundreds of chips work together like an assembly line, and where it works well and where it fails.25 min2026-09-01Decoding EAGLEEAGLE, a state-of-the-art way to speed up language model generation by drafting tokens at the feature level instead of the token level.8 min2026-08-31Decoding MedusaMedusa, a simple way to make a language model generate text 2 to 3 times faster by giving it several extra heads that guess multiple future tokens at once.10 min2026-08-27How do RNNs and Transformers differ?How RNNs and Transformers differ. These are the two main ways a computer reads a sequence like a sentence, and we will learn why one of them reads word by word, why the other reads everything at once, and when to use which one.7 min2026-08-25AI Is Only as Good as Our Definition of DoneOne simple idea, AI is only as good as our definition of done, which means the clear line we draw between a task that is finished and a task that is not. We will also see what a definition of done really is, why AI feels magical on the tasks that a machine can check, why it feels unreliable on the tasks that only a human can judge, how the loop that AI runs behind the scenes creates this exact gap, and how we can write a definition of done that turns a vague task into a checkable one.11 min2026-08-24How does Prefix Tuning work?Prefix Tuning, a cheap way to adapt a large language model to a new task without changing the model itself. It saves memory, saves money, and lets one big model serve many different tasks at once. We will also see why full fine-tuning is so expensive, how the prefix is added and trained without changing the model, how Prefix Tuning differs from full fine-tuning and prompt tuning and when to use which one based on our use case, where it falls short and how it compares with LoRA, and where it is used in the real world.25 min2026-08-21What is Graph Engineering?Graph Engineering, the practice of building an AI system as a graph of small steps connected by clear paths instead of one giant prompt or one endless loop. We will also see why we need it, what nodes and edges actually mean, how the state travels through the graph, how conditional edges take decisions, how cycles let the system do the work again, how parallel branches save time, how checkpoints let us pause and resume, and where it works well and where it fails.26 min2026-08-20What is Loop Engineering?Loop Engineering, the practice of designing the repeating cycle that an AI agent runs again and again until a task is actually finished. We will also see why we need it, what one turn of the loop looks like, the parts of the loop that we must control, how it is different from prompt engineering and context engineering, the common ways a loop breaks, the techniques that fix those breaks, and where it works well and where it fails.20 min2026-08-19The Lost in the Middle Problem in LLMsThe Lost in the Middle problem in LLMs, the strange behaviour where a model reads a very long text, uses the beginning and the end very well, and quietly ignores whatever is sitting in the middle. We will also see what a context window really means, how the accuracy forms a U-shaped curve, why the middle gets forgotten, how this silently breaks RAG systems and long conversations, how we can test our own model for it, and what we can do to fix it.22 min2026-08-18How Does LLM Watermarking Work?How LLM watermarking works, the hidden signal that a model quietly leaves inside the text it writes. We will also see why we need it, how an LLM picks one token at a time, how a secret key silently changes those choices without touching the meaning, how a detector finds that hidden pattern later, why the quality of the text does not break, how it is different from an AI text detector, and where it works well and where it fails.22 min2026-08-17Decoding Deep RL from Human PreferencesIn this blog, we are going to learn about Deep Reinforcement Learning from Human Preferences, the 2017 paper that started it all. It taught machines what we want by simply asking us to pick which of two behaviors looks better. This is the origin of RLHF, the technique behind ChatGPT.15 min2026-08-13Decoding InstructGPTIn this blog, we are going to learn about InstructGPT, the model that taught GPT-3 to actually follow our instructions, and the work that led directly to ChatGPT.16 min2026-08-12Decoding ColBERTIn this blog, we are going to learn about ColBERT, a retrieval method that keeps the fine-grained, word-by-word matching of a slow BERT reranker but makes it fast enough to search millions of passages, using a clever trick called late interaction.18 min2026-08-10How do LLM guardrails work?How LLM guardrails work. We will also see why we need guardrails, where they sit on the input and output of a model, how they work through code, and the best practices we follow when using them in the real world.13 min2026-08-07Cloud vs On-device Model DeploymentCloud vs On-device Model Deployment, the two places where an AI model can actually run and do its work. We will also see how Cloud Deployment and On-device Deployment differ from each other, how each one works with simple examples, why one of them is very powerful but far away while the other one is very close but limited, what the hybrid approach is, and when to use which one.28 min2026-08-06Encoder vs Decoder in TransformersEncoder vs Decoder in Transformers, the two building blocks behind almost every modern AI model that works with language. We will also see how the Encoder and the Decoder differ from each other, how each one works with simple examples, why one of them reads in both directions while the other one looks only backward, what the three types of Transformers are, and when to use which one.11 min2026-08-05What is Generative AI?What Generative AI is. We will understand what the word "generate" actually means, how Generative AI is different from the older AI, how it learns from a huge amount of examples, how it creates something completely new, where we use it every day, and the limitations we must know.13 min2026-08-03Prompt Injection in LLMsPrompt Injection in Large Language Models. We will also see why it happens, how an attacker uses it, why the obvious fixes fail, and how we can defend our AI applications against it in the real world.33 min2026-08-01Precision vs RecallPrecision vs Recall, the two numbers we use to measure how good a system is at making yes-or-no decisions. We will also see how Precision and Recall differ from each other and when to use which one, what the four possible outcomes of any such decision are, why these two numbers pull against each other, and how the cost of a mistake decides which one we must care about more.10 min2026-07-31What are Embeddings?Embeddings, one of the most important ideas behind modern AI like search engines, recommendations, and chatbots. We will also see why a computer cannot compare meaning on its own, how an embedding turns meaning into numbers so that similar things sit close together, how we measure that closeness, and where we use embeddings in the real world.18 min2026-07-30What are Agent Skills?Agent Skills. We will also see why we need them, what is inside a Skill, how the description makes an agent pick up the right Skill by itself, how progressive disclosure keeps the context window free, how Agent Skills differ from MCP, and how we can create our own Skill.19 min2026-07-28What is MCP (Model Context Protocol)?MCP (Model Context Protocol). We will also see the problem it solves, the pieces it is made of, how a request travels from the AI model all the way to a tool and back, and what we must be careful about while using it.15 min2026-07-27How does fine-tuning work?How Fine-tuning works. We will also see why we need it, how it works step by step with a simple example, how full fine-tuning and LoRA differ and when to use which one based on our use case.14 min2026-07-26What is OKF (Open Knowledge Format)?OKF (Open Knowledge Format). We will also see why the knowledge about our data stays scattered across many places, how OKF writes that knowledge down as a folder of plain markdown files which any AI agent or any tool can read, and where it fits along with MCP and Agent Skills in the real world.20 min2026-07-23How does Semantic Search work?How Semantic Search works. We will also see why we need it, how it actually works step by step, and where it is used in real systems like search engines, AI assistants, and recommendations.19 min2026-07-22How does Cursor work?How Cursor works. We will also see what Cursor is, why it is a code editor with an AI brain on top, how it indexes our codebase into embeddings and searches it by meaning, how Tab autocomplete, Chat, and Agent mode work, how Cursor applies changes through a diff, why it uses different models for different jobs, and how it tries to keep our code private.17 min2026-07-21How does context compaction work?How context compaction works in Large Language Models. We will also see why long conversations overflow the context window, how summarization shrinks the older messages without losing the important points, and where compaction is used in real AI agents.16 min2026-07-20How does Claude Code work?How Claude Code works. We will also see what Claude Code is, why a normal AI chatbot is not enough, how the agent loop drives it, what tools give it its eyes and hands, how it searches a big project and verifies its own work, and how CLAUDE.md, permissions, plan mode, subagents, and hooks fit together.19 min2026-07-16How does llama.cpp run LLMs on everyday hardware?How llama.cpp runs large language models on everyday hardware. We will also see what llama.cpp is, why it was created, how it shrinks huge models with quantization, how it loads them quickly, and how it shares work between the CPU and the GPU.18 min2026-07-15How does Model Quantization work?How Model Quantization works. We will also see why we need it, how it shrinks big AI models, and how it lets us run them on a laptop, a phone, or a single GPU.20 min2026-07-11How does Chain-of-Thought (CoT) Prompting work?How Chain-of-Thought (CoT) Prompting works. We will also see why a model that jumps straight to the answer often gets it wrong, how making it reason step by step fixes this, the difference between zero-shot and few-shot CoT, and where this technique is truly useful.13 min2026-07-10How does Prompt Chaining work?How Prompt Chaining works. We will also see why we need it, how it works step by step by passing the output of one prompt into the next, and where it is used in the real world to solve bigger tasks reliably.14 min2026-07-09How does PyTorch work?How PyTorch works. We will also see what a tensor is, how the computation graph and autograd work together to train a model, and why PyTorch uses the GPU to become one of the most popular tools in the real world.17 min2026-07-08How does Semantic Caching work?How Semantic Caching works. We will also see why traditional caching falls short for AI apps, how Semantic Caching uses embeddings and similarity to reuse past answers, and how setting the right threshold makes it work in the real world.15 min2026-07-07How does Hybrid Search work?How Hybrid Search works. We will also see why we need it, the two kinds of search it combines, how their results are merged together, and where it is used in real systems like RAG.18 min2026-07-06How does HyDE work in RAG?How HyDE works in RAG, which is the clever trick of searching with a fake answer. We will also see why searching with the plain question is weak, why a fake answer searches better, how HyDE works step by step with a worked example, and when to use it in the real world.15 min2026-07-05Prefill vs Decode: LLM Inference OptimizationPrefill vs Decode, the two phases of LLM inference, and how understanding them helps us optimize the speed of an LLM. We will also see how the prefill and decode phases work, how the KV cache connects them, how they differ and when to use which one based on our use case, and how we optimize each phase to make an LLM faster.33 min2026-07-03How does a GPU work for Deep Learning?How a GPU works for Deep Learning. We will also see why the GPU is perfect for deep learning, how they do so much math at the same time, and why companies like NVIDIA power almost all of modern AI.22 min2026-07-02How does LangGraph work?How LangGraph works. We will also see why we need it, what graphs, state, nodes, and edges are, how tools work and who actually calls them, how memory and human-in-the-loop fit in through a complete example, and when to use it in the real world.20 min2026-07-01How does LangChain work?How LangChain works. We will also see why we need it, what chains, prompts, memory, and output parsers are, how retrieval and agents fit in, and how the full flow works together in the real world.19 min2026-06-30How does SGLang work?How SGLang works. We will also see what problem it solves, how it makes serving large language models faster, and the clever ideas that make it special.23 min2026-06-29How does Approximate Nearest Neighbor (ANN) search work?Approximate Nearest Neighbor (ANN) Search, the idea that lets apps find "similar" things in a huge collection in the blink of an eye. It powers search engines, recommendation systems, face matching, and the memory behind modern AI chatbots. We will also see why the naive approach fails, how trees, hashing, clustering, and graphs make the search fast, and where ANN search is used in the real world.21 min2026-06-28How does a Google TPU work?How a Google TPU works. We will also see what a TPU is, why Google built it, how it is different from a CPU and a GPU, and how it makes machine learning fast.14 min2026-06-26How do Image Embeddings work?How image embeddings work. We will also see why we need image embeddings, how a computer turns a picture into numbers, how we measure the similarity between two of them, and where they are used in the real world.15 min2026-06-24How do Computer-Use Agents work?How computer-use agents work.15 min2026-06-22Decoding Sakana Fugu Technical ReportIn this blog, we are going to learn about Sakana Fugu, a family of AI models that work like a conductor for a team of other AI models.31 min2026-06-22How do Diffusion Language Models (DLMs) work?Diffusion Language Models (DLMs), a new way to make models write text. They promise to generate words in a different way than the LLMs we use today, and that too much faster in many cases.18 min2026-06-21How does an Embedding Cache work?How an Embedding Cache works. We will also see what an embedding is, why an Embedding Cache saves us a lot of money and time, how the cache key is built, and where it is used in real systems like RAG and semantic search.20 min2026-06-20How do World Models work?How World Models work. We will also see why we need them, how they actually learn an internal picture of an environment, and where they are used in real systems like robotics, game-playing, and video generation.21 min2026-06-17How does vLLM work?How vLLM works. We will also see why we need it, how it manages memory so cleverly, and where it is used in the real world to serve large language models to many users at once.21 min2026-06-14LLM Inference OptimizationTechniques like KV Cache, Paged Attention, Flash Attention, Speculative Decoding, Continuous Batching, and Prompt Caching are what make LLMs fast and scalable in production.6 min2026-06-13How does Function Calling work in LLMs?How Function Calling works in LLMs. We will see what it is, why we need it, the key insight behind it, and how it powers AI agents and assistants step by step.19 min2026-06-12How does GGUF work?How GGUF works. We will also see what problem it solves, what is stored inside a GGUF file, how quantization makes big models fit on a normal laptop, and where it is used in real tools.20 min2026-06-11How does Knowledge Distillation work?How Knowledge Distillation works. We will also see why we need it, how a small model learns from a big model, and how this lets us run powerful AI on a phone, on an edge device, and at low cost.19 min2026-06-10How does Token Streaming work?How Token Streaming works. We will also see why we need it, how the server and the browser talk to each other to make it happen, and where it is used in real systems like ChatGPT and Claude.19 min2026-06-09How does Prompt Caching work?How Prompt Caching works. We will also see why we need it, how it actually works inside a large language model, and where it is used in real systems like AI assistants and agents.17 min2026-06-08How does a Reranker work?How a Reranker works. We will also see where it sits in a search and RAG pipeline, why we need it, and how it makes our answers more accurate.21 min2026-06-07Joint Embedding Predictive Architecture (JEPA)Joint Embedding Predictive Architecture (JEPA). This is one of the most exciting ideas in modern AI, and it comes from Yann LeCun, one of the most respected researchers in the field. Do not worry, we will learn about each part of it slowly, in very simple words. By the end, a complete beginner will understand every single word.26 min2026-06-06How does a Vector Database work?How a Vector Database works. This is one of the most important pieces behind modern AI search, recommendations, and tools like ChatGPT that answer questions from our own documents.29 min2026-06-05Dropout in Neural NetworksDropout in Neural Networks. We will understand what it is, the problem it solves, how it works step by step with a simple example, and where it is used.13 min2026-06-04Generative Adversarial Networks (GANs)Generative Adversarial Networks (GANs), one of the most fascinating ideas in Machine Learning that can create brand new images, faces, and art that never existed before.17 min2026-06-03Diffusion ModelsDiffusion Models. We will understand what they are, why we need them, how they work step by step, and how they generate amazing images like the ones we see in tools such as DALL-E, Stable Diffusion, and Midjourney.17 min2026-06-02Variational AutoencodersVariational Autoencoders. We will understand what they are, why we need them, how they work step by step, and how they are able to generate brand new data like images that never existed before.18 min2026-06-01Continual Learning in LLMsContinual Learning in LLMs. We will understand what it is, why we need it, the big problem of catastrophic forgetting, the approaches used to solve it, and where it is used in the real world.13 min2026-05-31Multi-Head Attention in TransformersMulti-Head Attention in Transformers. We will understand what it is, how it works step by step, and why it gives Transformers their power to understand language so well.13 min2026-05-30Cross Attention in TransformersCross Attention in Transformers. We will understand what it is, how it works step by step, how it is different from Self Attention, and where it is used.14 min2026-05-29Self Attention in TransformersSelf Attention in Transformers. We will understand what it is, how it works step by step, and why it is the heart of modern Large Language Models like BERT and GPT.13 min2026-05-28AI Agent LoopThe AI Agent Loop - what it is, why an AI Agent needs it, the think-act-observe cycle that powers it, how the loop knows when to stop, and the common ways the loop fails.19 min2026-05-27AI Agent ObservabilityAI Agent Observability. We will also see why we need it, how it is different from normal software monitoring, what we must observe inside an agent, the key concepts like traces and spans, the metrics we must track, the tools we can use, and the best practices to follow.19 min2026-05-26How AI Agents CommunicateHow AI agents communicate. We will understand why agents need to communicate, the main ways they talk to each other, the message format, and the protocols that make agents work together to finish complex tasks.17 min2026-05-25AI SubAgentsAI SubAgents. We will understand what they are, why we need them, how they work, and how to use them to build AI systems that can handle big and complex tasks.8 min2026-05-24LLM EvaluationLLM Evaluation. We will understand what it is, why we need it, the main types of evaluation, the automatic metrics and benchmarks we can use, human evaluation, LLM as a Judge, task-specific and safety evaluation, the common challenges, and the best practices to follow.17 min2026-05-23AI Agent EvaluationAI Agent Evaluation. We will also see why it is different from LLM Evaluation, the types of evaluation we can do, the key metrics we must track, the methods we can use, and the best practices to follow.19 min2026-05-22AI OrchestrationAI Orchestration. We will understand what it is, why we need it, how it is different from AI Agents, and the common patterns we use to coordinate multiple LLMs, tools, and steps together to build real AI products.16 min2026-05-21LLM as a JudgeLLM as a Judge. We will also see how it works, why we need it, and how we can use it to evaluate the output of other LLMs.18 min2026-05-20Contrastive LearningContrastive Learning. We will also see how it works step-by-step and where it is used in the real world.13 min2026-05-19Recursive Language Models (RLMs)Recursive Language Models (RLMs), a new way of using language models to handle very large inputs that do not fit in the model's context window.11 min2026-05-18Group Relative Policy Optimization (GRPO)In this blog, we are going to learn about Group Relative Policy Optimization (GRPO). We will also see how GRPO works step-by-step and when to use it based on our use case.15 min2026-05-17Direct Preference Optimization (DPO)In this blog, we are going to learn about Direct Preference Optimization (DPO). We will also see how DPO works step-by-step and how it differs from RLHF (PPO).13 min2026-05-16Proximal Policy Optimization (PPO)In this blog, we are going to learn about Proximal Policy Optimization (PPO). We will also see how PPO works step-by-step and how it is used in training Large Language Models with RLHF.12 min2026-05-15Batch Normalization vs Layer NormalizationIn this blog, we are going to learn about Batch Normalization vs Layer Normalization. We will also see how Batch Normalization and Layer Normalization differ from each other and when to use which one.8 min2026-05-14Reinforcement Learning from Human Feedback (RLHF)Reinforcement Learning from Human Feedback (RLHF), the training technique that turns a raw pre-trained LLM into a helpful, honest, and safe assistant by teaching it from human preferences.19 min2026-05-13Autoregressive ModelsAutoregressive Models, the family of models that generate one piece at a time by predicting the next step from the past.18 min2026-05-12Large Reasoning Models (LRMs)Large Reasoning Models (LRMs), how they are different from standard Large Language Models, how they think before they answer, how they are trained, and when we must use them.18 min2026-05-11Continuous Batching in LLMsContinuous Batching, a technique that lets LLM servers handle many more users at the same time by keeping the GPU busy at every single step of generation.18 min2026-05-11Small Language Models (SLMs)Small Language Models (SLMs), what counts as small, why they matter, where they shine, and the trade-offs we must keep in mind.18 min2026-05-10Multimodal AIMultimodal AI, what it means, why it matters, how it works, and where we use it in the real world.13 min2026-05-09LLM RoutingLLM Routing, why it matters, and how to send each user query to the right LLM based on cost, latency, and quality.15 min2026-05-08Context EngineeringContext Engineering - what it is, why it has become the most important skill for building reliable AI applications, how it differs from Prompt Engineering, the components that make up the context, common patterns like RAG, few-shot examples, tools, and memory, and the best practices and common mistakes to keep in mind.19 min2026-05-07Reflection AgentThe Reflection Agent - what it is, how it is built, its anatomy, how it generates, critiques, and revises its own work, and how to handle its common failure modes.15 min2026-05-06Speculative DecodingSpeculative Decoding - what it is, why LLM generation is slow without it, how a small draft model and a big target model work together to produce tokens faster, the rejection sampling math that guarantees no quality loss, real numbers showing the 2x to 3x speedup, where it is used in production, and the trade-offs to watch out for.19 min2026-05-05GraphRAGGraphRAG and how it improves retrieval by using a knowledge graph along with vector search.12 min2026-05-04Plan-and-Execute AgentThe Plan-and-Execute Agent - what it is, its anatomy, how it plans and runs the steps, how it differs from a ReAct Agent, and how to handle its common failure modes.14 min2026-05-01Agentic RAGAgentic RAG - what it is, why standard RAG falls short, the agentic RAG loop, the three building blocks, the common patterns, when to use it, and the limitations to keep in mind.13 min2026-04-30ReAct AgentThe ReAct Agent - what it is, how it is built, its anatomy, how it thinks and acts, and how to handle its common failure modes.18 min2026-04-29Multi-Agent SystemsMulti-Agent Systems - what they are, the three pillars that hold them together, the common agent roles, how agents communicate and coordinate, the trade-offs, and when to use them.19 min2026-04-28AI Agent MemoryAI Agent Memory - why agents need it, the memory stack, the four core operations (write, read, update, forget), how memory flows at runtime, and the common mistakes.15 min2026-04-27AI Agent ExplainedThe AI Agent - what it is, how it is different from a plain LLM, its five core parts, how it works end to end, the main types, and when to use one.20 min2026-04-25RMSNorm (Root Mean Square Layer Normalization)RMSNorm, a faster and simpler alternative to Layer Normalization that powers most modern Large Language Models like Llama, Mistral, Gemma, Qwen, PaLM, and DeepSeek.12 min2026-04-24Decoding DeepSeek-V4DeepSeek-V4, the new family of open Mixture-of-Experts language models that natively supports a one-million-token context with dramatically lower inference cost.19 min2026-04-24LoRA - Low-Rank Adaptation of LLMsLoRA - Low-Rank Adaptation of Large Language Models.13 min2026-04-23Math Behind RoPE (Rotary Position Embedding)The math behind Rotary Position Embedding (RoPE) and why it is used in modern Large Language Models.15 min2026-04-22Grouped Query AttentionGrouped-Query Attention (GQA) and how it differs from Multi-Head Attention (MHA).17 min2026-04-20Math Behind Cross-Entropy LossThe math behind Cross-Entropy Loss with a step-by-step numeric example.16 min2026-04-17Math Behind Gradient DescentThe math behind gradient descent with a step-by-step numeric example.13 min2026-04-15Decoding Vision Transformer (ViT)The Vision Transformer (ViT) by decoding how it splits an image into patches, turns those patches into tokens, and processes them with a transformer to classify the image.14 min2026-04-13Feed-Forward Networks in LLMsFeed-Forward Networks in LLMs - understanding what they are, how they work inside the Transformer architecture, why every Transformer layer needs one, and what role they play in making Large Language Models so powerful.20 min2026-04-11Decoding Flash Attention in LLMsFlash Attention by decoding it piece by piece - understanding why standard attention is slow, what makes Flash Attention fast, how it uses GPU memory cleverly, and why it is used in almost every modern Large Language Model (LLM).22 min2026-04-09Mixture of Experts ExplainedThe Mixture of Experts (MoE) architecture - understanding what experts are, how the router picks them, why MoE makes large models faster and cheaper, and why it powers many of today''s most powerful Large Language Models (LLMs).15 min2026-04-07Decoding Transformer ArchitectureThe Transformer architecture by decoding it piece by piece - understanding what each component does, how they work together, and why this architecture powers every modern Large Language Model (LLM)19 min2026-04-06Math Behind BackpropagationThe math behind backpropagation in neural networks.15 min2026-04-05Math behind √dₖ Scaling Factor in AttentionWhy we scale the dot product attention by √dₖ in the Transformer architecture with a step-by-step numeric example.16 min2026-04-03Math behind Attention - Q, K, and VThe math behind Attention - Query(Q), Key(K), and Value(V) with a step-by-step numeric example.13 min2026-04-02Harness Engineering in AIHarness Engineering in AI.10 min2026-03-31Byte Pair Encoding in LLMsBPE (Byte Pair Encoding) - the tokenization algorithm used by most modern Large Language Models (LLMs) to break text into smaller pieces before processing it.11 min2026-03-29Paged Attention in LLMsPaged Attention, a technique that solves the memory waste problem of KV Cache, allowing LLMs to serve many more users at the same time.10 min2026-03-27KV Cache in LLMsKV Cache - where K stands for Key and V stands for Value - and why it is used in Large Language Models (LLMs) to speed up text generation.11 min2026-01-08Causal Masking in AttentionThe Causal Masking in Attention.9 min2025-12-10Linear Regression vs Logistic RegressionLinear Regression vs Logistic Regression in Machine Learning.6 min2025-12-09Supervised vs Unsupervised LearningSupervised vs Unsupervised Learning in Machine Learning.5 min2019-08-02What is Bias In Artificial Neural Network?What is Bias In Artificial Neural Network.3 min2019-08-02Feature Engineering for Machine LearningThe Feature Engineering for Machine Learning.5 min2019-08-02How Does The Machine Learning Library TensorFlow Work?How the Machine Learning library TensorFlow works.9 min2019-08-02What Are L1 and L2 Loss Functions?The L1 and L2 Loss functions.3 min2019-08-02What is Machine Learning?What is Machine Learning.10 min2019-08-02Recurrent Neural NetworkThe Recurrent Neural Network.4 min2019-08-02Regularization In Machine LearningThe Regularization In Machine Learning.3 min2019-08-02What is Reinforcement Learning?Reinforcement Learning, the branch of machine learning where an agent learns to make decisions by interacting with an environment and getting rewards or penalties for its actions.14 min