Guides & Explainers
In-depth written guides on AI concepts, from beginner to advanced
The NIST AI Risk Management Framework Explained
The NIST AI Risk Management Framework in plain words: the seven traits of trustworthy AI, the four functions, the Generative AI Profile's 12 risks, and vs the EU AI Act.
The EU AI Act Explained: Risk Levels, Bans and Key Dates
The EU AI Act in plain words: the four risk levels, the nine banned practices, rules for ChatGPT-style models, every key date to 2028, and the 2026 AI Omnibus.
How to Run AI Models Locally: Ollama, llama.cpp and vLLM
How running an open-weight AI model on your own computer works: what Ollama, llama.cpp and vLLM each do, quantisation, hardware, and OpenAI-compatible APIs.
What Is MCP? The Model Context Protocol Explained for Beginners
What the Model Context Protocol (MCP) is, in plain English: hosts, clients and servers, MCP connectors, tools, and how AI apps use them - with a diagram and FAQ.
Segment Anything (SAM) Explained: Click-to-Cut-Out AI
What Meta's Segment Anything Model does: prompts, its three-part design, the 1-billion-mask SA-1B dataset, zero-shot results, and SAM 2 for video.
Vision Transformer (ViT) Explained: How an Image Becomes Patches
How the Vision Transformer cuts an image into 16x16 patches and reads them like words, why it needed large datasets, its three sizes, and ViT vs CNN.
GPT-6 Astra Explained: Price, Context Window and Specs
GPT-6 Astra explained: OpenAI's first GPT-6 model at $10/$50 per million tokens, 1.05M context, 128K output, April 2026 cutoff, five effort levels.
Claude Fable 5.1 Explained: Price, Cache and Specs
What Claude Fable 5.1 is: $10/$50 per million tokens like Fable 5, cache reads cut to $0.25, 1M context, 128k output, adaptive thinking and effort levels.
Qwen3.7 Max Explained: Price, Context and Specs
Alibaba's Qwen3.7 Max explained: $2.50/$7.50 per million tokens internationally, $1.65/$4.951 in Beijing, 1M context, 131K output, and Qwen3.8 compared.
Muse Spark 1.2 Explained: Meta's Model, Price and Modes
Meta's Muse Spark 1.2 explained: $1.25/$4.25 per million tokens, or $0.10/$0.20 in Contributor mode, 1M context, text, image, video and audio input.
DeepSeek V4-Pro Explained: Peak and Off-Peak Pricing
DeepSeek V4-Pro explained: $1.32/$3.96 per million tokens at peak, half off-peak, when peak hours are, 1M context, 384K output, MIT open weights.
Grok 4.5 Explained: Price, Specs and How It Compares
xAI's Grok 4.5 explained: $2/$6 per million tokens under 200k prompt tokens, double above, 500k context, reasoning efforts, and Grok 4.6 and 4.7 compared.
Showing 13–24 of 45 guides