LLM Architecture
Popularity Index: 27 Updated at 2026-10-10 01:46 UTCSites
Subcategories 11
Topics 14
Embeddings: what the numbers actually represent
RAG versus long context: which to choose?
Why a larger context does not mean better recall
Parameters versus data: which drives capability?
Rotary position embeddings explained
Scaling laws and where they stopped holding
The decoder-only design and why it won
Quantization: squeezing a model to fit
Mixture of experts models and what they change
State space models as an alternative to attention
Tokenization and why models miscount letters
How the transformer attention mechanism works in plain language
Why context windows are expensive to extend
Do long system prompts still matter?
Parent categories
Hot Categories
Just updated
Qwen4-Max
Jensen Huang
ChatGPT
AI in Search
Binance
North Korea
iPhone Duo
PHP2Shell
Tiktok
Gaming
Mid-Autumn Festival
Summer
Geography
Premier League
Arsenal
Middle East
Artificial general intelligence
iPhone
Anthropic
OpenAI
Most viewed