# Explainers — Page 3 — QANATONE

> Explainers on AI and search technology: what each concept is and how it works, shown with examples. Page 3.

Kaynak: https://www.qanatone.com/en/nedir/sayfa/3/

---

[Home](https://www.qanatone.com/en/) Nedir

# Nasıl çalıştığını anlatıyoruz. (38)

Konunun ne olduğunu ve nasıl işlediğini örnekle anlatıyoruz. Tanım yazıları eskimez — haberler gündem, burası açıklama.

[News](https://www.qanatone.com/en/haber/)[Explainers](https://www.qanatone.com/en/nedir/) [**Model Type · SAM** 15 September 2026 2 min read ## What is the Segment Anything Model (SAM)? SAM is an image segmentation model from Meta that can cut out any object in an image at pixel level with a single click. Read](https://www.qanatone.com/en/nedir/sam-nedir/)[**Model Type · SLM** 15 September 2026 2 min read ## What is a small language model (SLM)? An SLM is a much smaller language model that can run even on a phone or laptop. It is fast and cheap for focused tasks. Read](https://www.qanatone.com/en/nedir/slm-nedir/)[**Marketing · Social Media** 15 September 2026 2 min read ## What is social media marketing? A strategy for 2026 Social media marketing is using content and ads on social platforms to reach business goals. Here is how to build a strategy that pays off. Read](https://www.qanatone.com/en/nedir/sosyal-medya-pazarlamasi-nedir/)[**Prompting · System Prompt** 15 September 2026 2 min read ## What is a system prompt and how is it different? A system prompt is the standing set of instructions an AI app gives the model in the background, setting the assistant role and rules. Read](https://www.qanatone.com/en/nedir/system-prompt-nedir/)[**Model Settings · Temperature** 15 September 2026 2 min read ## What is temperature in AI models? Temperature sets how much risk a model takes when picking the next word. Low values give consistent answers, high values varied ones. Read](https://www.qanatone.com/en/nedir/temperature-nedir/)[**Core Concept · Token** 15 September 2026 2 min read ## What is a token in AI and how is it counted? A token is the smallest piece of text a language model works with. Pricing, speed and how much it can read at once are measured in tokens. Read](https://www.qanatone.com/en/nedir/token-nedir/)[**Marketing · Turkey** 15 September 2026 2 min read ## Digital marketing in Turkey: the market in numbers Three quarters of media spending in Turkey now goes to digital. The size of the market and what it means for businesses, in numbers. Read](https://www.qanatone.com/en/nedir/turkiye-dijital-pazarlama/)[**Guide · Free Tools** 15 September 2026 1 min read ## Free AI tools: what is available and what are the limits? ChatGPT, Gemini, Claude and Copilot all have free versions, with limits. How to get the most from them and what risks to keep in mind. Read](https://www.qanatone.com/en/nedir/ucretsiz-yapay-zeka/)[**Architecture · Vector Database** 15 September 2026 2 min read ## What is a vector database? A vector database stores embedding vectors and quickly finds the records closest in meaning to a query. It is the backbone of RAG systems. Read](https://www.qanatone.com/en/nedir/vektor-veritabani-nedir/)[**Model Type · VLM** 15 September 2026 2 min read ## What is a vision-language model (VLM)? A VLM is an AI model that understands images and text together. It can describe a photo or read and interpret the amounts on an invoice. Read](https://www.qanatone.com/en/nedir/vlm-nedir/)[**Prompting · Zero-shot** 15 September 2026 2 min read ## What is zero-shot prompting? Zero-shot means giving a model a task with instructions only and no examples. The model relies on what it learned during training. Read](https://www.qanatone.com/en/nedir/zero-shot-nedir/)[**Core Concept · LLM** 12 September 2026 6 min read ## What are large language models (LLMs) and how do they work? LLMs are probabilistic models with billions of parameters, trained on internet text. A next-word prediction game yielding uncanny capabilities at scale. Read](https://www.qanatone.com/en/nedir/buyuk-dil-modelleri-nedir/)

[Previous](https://www.qanatone.com/en/nedir/sayfa/2/)
- [1](https://www.qanatone.com/en/nedir/)

- [2](https://www.qanatone.com/en/nedir/sayfa/2/)

- 3

- [4](https://www.qanatone.com/en/nedir/sayfa/4/)

[Next](https://www.qanatone.com/en/nedir/sayfa/4/)