The short answer BERT (Bidirectional Encoder Representations from Transformers) vs GPT (Generative Pre-trained Transformer) is not a rivalry between two general-purpose models. Both come from the same 2017 Transformer paper, which described an encoder and a decoder together. BERT kept…
The short answer MCP (Model Context Protocol) vs function calling is not a choice between two rivals. Function calling is a capability of the model’s application programming interface (API). The application sends tool definitions with the request. Then the model…
The short answer Temperature vs top-p differ in what they touch inside a model’s output. Temperature rescales every logit before softmax runs, so it reshapes the whole probability distribution. Below T = 1 it sharpens the leading token’s share. Above…
The short answer Lossless vs lossy decomposition comes down to one join. A split of relation R into R1 and R2 is lossless when their natural join returns exactly R. No rows go missing, and none get added. Three conditions…
The short answer Go-Back-N vs Selective Repeat comes down to the receiver window. Go-Back-N pins that window at exactly 1. It accepts frames only in strict order, and discards anything that arrives out of place. Selective Repeat gives the receiver…
The short answer Semaphore vs mutex comes down to ownership. A mutex is a lock: one thread locks it, and only that same thread may unlock it. A semaphore works differently. It is an integer counter with two atomic operations,…
The short answer Z-buffer vs painter’s algorithm is about where the visibility decision happens. The painter’s algorithm sorts every polygon by depth. Then it paints them back to front, so nearer surfaces cover farther ones. That sort costs work, and…
The short answer LoRA vs QLoRA vs full fine-tuning comes down to what gets frozen and what gets trained. Full fine-tuning updates every parameter, so memory has to hold the weights, the gradients, and the optimizer state together. For a…
The short answer Quantization vs distillation solves the same problem in different ways. Quantization keeps the same model and stores each weight in fewer bits. The parameter count never changes; only the bytes per weight do. Distillation, instead, trains a…
You cannot copy content of this page
