Tech AI News - 테카이

AI Glossary

How It Works

13 posts

Hybrid search: why a vector DB alone isn't enough

Embedding-based semantic search often misses exact strings like error codes or product names. Hybrid search runs BM25 keyword search alongside vector search and merges results with methods like RRF.

How It Works· 5 min

LoRA — if it's fine-tuning, why isn't the whole model retrained?

LoRA doesn't retrain the whole model — it freezes the original weights and trains only two small low-rank matrices per layer, which is why trainable parameters shrink by thousands of times while GPU memory savings are far more modest.

How It Works· 5 min

Reasoning models — why thinking AI costs more

Reasoning models generate hidden thinking tokens before answering, and those tokens are billed as output. We compare OpenAI/Anthropic docs and DeepSeek R1 to explain the price gap and how to tune costs.

How It Works· 4 min

Vector DB — A purpose-built search warehouse for AI

A vector DB converts text and images into numeric coordinates (embeddings) to quickly find semantically similar items. It’s core to RAG, but only makes sense after weighing scale, latency, and search goals.

How It Works· 4 min

RAG — how to know the latest information without fine-tuning

RAG retrieves relevant documents at query time and inserts them into the prompt instead of retraining the model. It’s often better than fine-tuning for fast-changing knowledge or citation needs, but it doesn’t eliminate hallucinations.

How It Works· 4 min

RAG — How to keep models up to date without fine-tuning

RAG retrieves relevant documents at query time and injects them into the prompt instead of retraining the model. It shines when knowledge changes often or citations are required, but it does not eliminate hallucinations.

How It Works· 4 min

Training vs. Inference — When Does AI Actually Get Smarter?

It feels like AI gets smarter the more you talk to it, but it does not actually learn anything new mid-conversation. This article lays out how training and inference differ, and why test-time compute became the AI industry's new buzzword in 2026, with data.

How It Works· 5 min

Transformer — The Ancestor of Every AI Today

From GPT to Gemini to Claude, every major AI model in 2026 runs on the Transformer architecture Google published in 2017. This article covers how self-attention works and the line of variations from decoder-only models to MoE and Mamba hybrids.

How It Works· 5 min

Attention — How AI Picks Out 'What Matters' in a Sentence

Attention is the mechanism by which AI understands long text not by remembering every word equally, but by concentrating on the few words it needs right now. This article explains why cost grows as context gets longer, and how optimizations like GQA and MLA affect real-world response speed and pricing.

How It Works· 6 min