Chisato · · 5 min read What Is a World Model in AI?
A world model is an AI system's internal simulation of how its environment changes, letting it predict outcomes before acting.
#AI
#Machine Learning
#Computer Science
Topic
#Machine Learning
66 posts tagged “Machine Learning”.
Chisato · · 5 min read 
Chisato · · 4 min read Precision vs Recall, Explained
Precision measures how many of a model's positive predictions were correct; recall measures how many actual positives it found. Why you can't max both.
#AI
#Machine Learning
#LLMs
Chisato · · 4 min read What Is Logit Bias? Steering LLM Output Per Token
Logit bias nudges an LLM's token probabilities up or down before sampling, letting you ban, force, or discourage specific words without a prompt.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read What Is Instruction Tuning? LLM Training Explained
Instruction tuning trains a language model on prompt-response pairs so it follows directions instead of just predicting text. How it works and where it fits.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is a Neural Network? The Basics Explained
A neural network is layers of weighted connections that learn patterns from data. How neurons, activation functions, and training actually work.
#AI
#Machine Learning
#LLMs
Chisato · · 4 min read What Is a Vision Transformer (ViT)?
A Vision Transformer applies the transformer architecture to images by splitting them into patches processed with self-attention instead of convolutions.
#AI
#Machine Learning
#Deep Learning
Chisato · · 5 min read Supervised vs Unsupervised vs Reinforcement Learning
Three ways machine learning models learn: from labeled examples, from patterns in unlabeled data, or from trial-and-error reward signals.
#AI
#Machine Learning
#Computer Science
Chisato · · 4 min read Positional Encoding in Transformers, Explained
Positional encoding gives transformers word order by adding position signals to token embeddings, since self-attention alone is order-blind.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Model Collapse? AI Training on AI Output
Model collapse is the degradation that happens when a generative model is repeatedly trained on data produced by earlier generations of itself.
#AI
#Machine Learning
#LLMs
Chisato · · 5 min read What Is Reward Hacking in AI Systems?
Reward hacking is when an AI system optimizes its literal reward signal in ways that satisfy the metric but violate what the designer actually wanted.
#AI
#Machine Learning
#AI Safety
Chisato · · 4 min read How Backpropagation Works in Neural Networks
Backpropagation is the algorithm that trains neural networks by computing how each weight contributed to the error, then adjusting it. Here's the mechanism.
#AI
#Machine Learning
#LLMs
Chisato · · 4 min read What Is Vector Quantization? Compressing Embeddings
Vector quantization compresses high-dimensional embeddings into compact codes, shrinking memory and search cost with a small accuracy trade-off.
#AI
#Machine Learning
#LLMs
Chisato · · 4 min read Overfitting vs Underfitting: How ML Models Fail
Overfitting memorizes training data and fails on new inputs; underfitting fails to learn the pattern at all. How to spot each and what fixes each one.
#AI
#Machine Learning
#Computer Science
Chisato · · 4 min read GANs Explained: How Generative Adversarial Networks Work
A GAN pits a generator against a discriminator in a training loop that produces realistic synthetic data. How the adversarial setup works.
#AI
#Machine Learning
#Deep Learning
Chisato · · 4 min read Self-Attention Explained: How Transformers Read Context
Self-attention lets each token in a sequence weigh every other token when building its representation, which is how transformers understand context.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Neural Network Pruning Explained
Neural network pruning removes redundant weights or neurons after training to shrink a model without retraining from scratch. How it works.
#AI
#Machine Learning
#Performance
Chisato · · 4 min read What Is a Foundation Model in AI?
A foundation model is a large model pretrained on broad data, then adapted for many downstream tasks via fine-tuning, RAG, or prompting alone.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Semantic Search vs Keyword Search: What's the Difference?
Keyword search matches literal terms; semantic search matches meaning via vector embeddings. How each works, and why most production systems use both.
#AI
#Machine Learning
#LLMs
Chisato · · 4 min read What Is Gradient Descent? How Models Learn
Gradient descent is the optimization algorithm that trains neural networks, nudging weights downhill along the loss function's gradient.
#AI
#Machine Learning
#LLMs
Chisato · · 5 min read What Is a Vision-Language Model (VLM)?
A vision-language model processes images and text together, jointly grounding visual content in language. How VLMs are trained and what they're used for.
#AI
#Machine Learning
Chisato · · 5 min read What Is Test-Time Compute? Inference-Time Scaling
Test-time compute is extra computation an AI model spends while answering, not while training — trading latency and cost for better answers.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is LLM-as-a-Judge?
LLM-as-a-judge uses one language model to score another model's outputs against a rubric, replacing slow human review for large-scale evaluation.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is an AI Model Card?
A model card is a standardized document describing an AI model's intended use, training data, evaluation results, and limitations before deployment.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read What Is a Feature Store? ML Feature Management Explained
A feature store centralizes how machine learning features are computed, stored, and served — keeping training and production predictions consistent.
#AI
#Machine Learning
#Data Engineering
Chisato · · 5 min read What Is Catastrophic Forgetting in AI Fine-Tuning?
Catastrophic forgetting is when training a model on new data erases skills it already had. Why it happens during fine-tuning, and how teams work around it.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is DPO? Direct Preference Optimization Explained
DPO tunes a language model on human preference data directly, without training a separate reward model or running reinforcement learning.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Constitutional AI? Training Models on Principles
Constitutional AI trains language models to critique and revise their own outputs against a written set of principles, reducing reliance on human labels.
#AI
#LLMs
#Machine Learning
Chisato · · 6 min read Lilian Weng Rejoins OpenAI to Lead Self-Improvement
Thinking Machines co-founder Lilian Weng left the startup citing health, then rejoined OpenAI within days to lead a new recursive self-improvement research team.
#AI
#OpenAI
#Machine Learning
Chisato · · 4 min read LLM Grounding Explained: Tying Answers to Real Data
Grounding connects an LLM's output to verifiable external data instead of relying on what it memorized during training, reducing hallucinations. How it works.
#AI
#LLMs
#Machine Learning
Chisato · · 7 min read Gemini Robotics 2: Google's Whole-Body Humanoid AI
Google DeepMind released Gemini Robotics 2, a three-model suite that controls humanoids feet-to-fingertips, plans multi-step tasks, and adapts to new robots in hours.
#AI
#Robotics
#Google
Chisato · · 4 min read RAG vs Fine-Tuning: When to Use Each
RAG retrieves relevant documents at query time; fine-tuning bakes new behavior into model weights. How to choose based on what actually needs to change.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read Batch vs Real-Time Inference: How AI Serving Differs
Batch inference processes large volumes of input on a schedule; real-time inference answers one request as fast as possible. How the two serving modes differ.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Prompt Engineering?
Prompt engineering is the practice of structuring instructions to get reliable, accurate output from an LLM. Core techniques and common pitfalls.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Model Distillation vs Quantization: Shrinking LLMs Compared
Distillation trains a smaller model to mimic a larger one; quantization shrinks an existing model's number precision. How the two techniques differ.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is a Reranker? Why RAG Pipelines Need One
A reranker re-scores a retriever's candidate results with a slower, more accurate model, fixing the precision gap that pure vector search leaves behind.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read RAG Chunking Strategies Explained
How you split documents into chunks determines what a RAG system can retrieve. Fixed-size, semantic, and recursive chunking compared, with tradeoffs.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Federated Learning?
Federated learning trains a shared model across many devices without moving their raw data, sending only model updates back to a central server.
#AI
#Machine Learning
#Security
Chisato · · 4 min read Beam Search Explained: How LLMs Pick Tokens
Beam search keeps the top-k most likely sequences at each decoding step instead of just one, trading compute for better output than greedy decoding.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Synthetic Data? AI Training Explained
Synthetic data is artificially generated training data that mimics real-world patterns without exposing actual records. How it's made and used.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read In-Context Learning vs Fine-Tuning for LLMs
In-context learning teaches a model a task through examples in the prompt; fine-tuning updates the model's weights permanently. How they compare.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Temperature vs Top-p vs Top-k: LLM Sampling Explained
Temperature, top-p, and top-k are the three main knobs that control how an LLM picks its next token — and why outputs get more random or more repetitive.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is an LLM Eval? Testing Model Outputs Explained
An LLM eval is a structured test suite that scores a model's outputs against a standard, letting you compare models and catch regressions systematically.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read What Is LoRA? Low-Rank Adaptation Explained
LoRA fine-tunes a large model by training small low-rank matrices instead of its full weights. How it works, why it's cheap, and where it falls short.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Multimodal AI? Beyond Text-Only Models
A multimodal AI model processes and generates more than one type of data — text, images, audio — in a single unified system. Here's how it works.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is a System Prompt? How LLMs Get Instructions
A system prompt is the hidden instruction set that shapes an LLM's persona, tone, and boundaries before any user message arrives — how it works.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Why LLMs Hallucinate, and How to Reduce It
An LLM hallucination is a fluent, confident output that is factually wrong — a byproduct of next-token prediction, not a bug you can simply patch.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is Speculative Decoding? LLM Inference Explained
Speculative decoding speeds up LLM text generation by having a small draft model guess tokens the large model verifies in one pass. Here's how it works.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Chain-of-Thought Prompting Explained
Chain-of-thought prompting asks an LLM to reason step by step before answering, improving accuracy on multi-step problems by making its work explicit.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read Zero-Shot vs Few-Shot Prompting: What's the Difference
Zero-shot prompting asks an LLM to perform a task with no examples; few-shot includes sample input-output pairs in the prompt. When to use each.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is LLM Temperature? Sampling Parameters Explained
Temperature controls how random an LLM's token choices are. How it works alongside top-p and top-k, and how to pick a value for your use case.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read What Is RLHF? Reinforcement Learning Explained
RLHF trains a language model to match human preferences using a reward model and reinforcement learning. How the training pipeline actually works.
#AI
#LLMs
#Machine Learning
Chisato · · 5 min read What Is Tokenization in LLMs? Tokens Explained
Tokenization is how a language model chops text into tokens — the units it actually reads and bills. How it works, why words split oddly, and why it matters.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read What Is a Context Window? LLM Memory, Explained
An LLM's context window is the maximum text it can consider at once — prompt plus response, measured in tokens. Why it matters and how to work within it.
#AI
#LLM
#Machine Learning
Chisato · · 5 min read What Is Model Distillation? Smaller Models, Explained
Model distillation trains a small student model to mimic a larger teacher. How it works, how it differs from quantization and pruning, and its limits.
#AI
#LLMs
#Machine Learning
Chisato · · 3 min read What Are Vector Embeddings? Meaning as Numbers
A vector embedding turns text, images, or audio into numbers where similar meanings land close together — the foundation of semantic search and RAG.
#AI
#Machine Learning
#Databases
Chisato · · 4 min read What Is a Diffusion Model? How AI Makes Images
Diffusion models generate images by learning to reverse a gradual noising process. How they work, what powers Stable Diffusion, and how they compare to GANs.
#AI
#Machine Learning
Chisato · · 3 min read What Is a GPU? Why AI Runs on Graphics Chips
A GPU packs thousands of small cores built for parallel arithmetic. Originally for graphics, it's now the engine behind training and running AI models.
#Hardware
#AI
#Machine Learning
The Lycoris Team · · 5 min read Noam Shazeer Leaves Google DeepMind for OpenAI
Noam Shazeer, a co-author of the Transformer paper that underpins modern AI, is leaving Google DeepMind for OpenAI — the AI talent war's latest marquee move.
#AI
#LLMs
#Machine Learning
Chisato · · 3 min read Gemini 3: Google's New Flagship AI Model Family
Google released Gemini 3 — Pro, Flash, Deep Think, and a 3.5 series — across the Gemini app, AI Studio, and Vertex AI. Here's the lineup.
#AI
#LLMs
#Machine Learning
The Lycoris Team · · 2 min read Apple Rebuilds Siri Around Generative AI
At WWDC 2026, Apple unveiled 'Siri AI' — a ground-up redesign powered by Google's Gemini through a multi-billion-dollar partnership. Here's what changed and why.
#AI
#LLMs
#Machine Learning
Chisato · · 3 min read What Is Fine-Tuning? Specializing AI Models
Fine-tuning continues training a pretrained model on a task-specific dataset. How it works, when to use it over prompting or RAG, and what can go wrong.
#AI
#LLMs
#Machine Learning
Chisato · · 4 min read Open-Source AI Models Are Closing the Gap
Open-weight AI models are catching up to the best closed systems on many tasks — and you can run them yourself. What's driving the shift and what it means.
#AI
#Open Source
#Machine Learning
Chisato · · 4 min read What Is a Transformer? The Architecture Behind Modern AI
The transformer is the architecture behind modern LLMs. How attention, tokens, and stacked layers combine to make today's AI work.
#AI
#LLMs
#Machine Learning
Chisato · · 9 min read What Are LLMs? Large Language Models, Explained
What are LLMs and how do they work? A plain-English guide to large language models: tokens, training, real examples, and what they still get wrong.
#AI
#LLMs
#Machine Learning
Chisato · · 3 min read Reasoning Models: How 'Thinking' AI Actually Works
Reasoning models 'think' before they answer, trading inference time for accuracy on hard problems. Here's how test-time compute, adaptive thinking, and effort work.
#AI
#LLMs
#Machine Learning
Chisato · · 7 min read What Is Mixture of Experts (MoE)? Sparse Models, Explained
Mixture of Experts (MoE) scales LLMs by activating only a few experts per token. How routing, sparse activation, and load balancing actually work.
#AI
#LLMs
#Machine Learning