Guides & How-tos · Worked examples · Real numbers

AI & ML guides

Step-by-step how-tos, head-to-head comparisons and honest roundups — every guide worked through with current figures, then backed by a RECATOOLS calculator or AI-directory entry so you can act on it.

185 guides published 15 topic areas Latest guide Aug 2026

Tagged LLM · 24 guides

All 185 AI & ML 47 Finance 27 Cybersecurity 24 Developer Tools 20 Science 10 Chinese Culture 9

Advertisement

An antique balance beam mounted on a wall beside a wooden measuring rod, its pan hanging empty — an instrument that only tells you anything when it is weighed against a known standard.

We Went Looking for What AI Is Bad At. We Found a Bill Instead.

Every business owner wants a map of where AI is reliable and where it is not. We built five task types — drafting to spe...

A researcher at a laboratory bench, back to the camera, surrounded by rows of identical glassware — the shape of a controlled comparison, where only one thing is allowed to differ.

We Tested the Prompting Folklore — 474 Answers Later, Nothing Had Changed

Tell the model it is an expert. Offer it a $200 tip. Threaten it. Say please. Add "let's think step by step". We ran all...

Close-up of vintage wooden letterpress blocks spelling 'pleasure' on paper.

Why AI Cannot Spell — What Image, Video and Voice Models Do Instead

A language model emits one symbol at a time, in order. An image model starts from noise and refines the whole canvas at...

Advertisement

Close-up of a vintage industrial control panel with multiple buttons and switches.

How to Spend Fewer Tokens — and Why That Is the Fourth Thing to Try

Every guide to controlling an AI bill opens by telling you to trim your prompt. We ran the arithmetic over all 27 models...

A woman searching a wall of library card-catalogue drawers, pulling one open — a filing system is only useful when its drawers match what is being filed.

What Am I Actually Choosing Between? We Sorted 1,347 AI Tools by Shape

The usual answer is five neat categories — chat assistants, copilots, command-line agents, autonomous runtimes, model pr...

Wooden closed sign hanging on a shop window, with blurred background outside.

Do You Need Fine-Tuning? Two of the Big Three Are Taking It Away

The usual case against fine-tuning is that it is expensive. That case is wrong — a small training run costs about four d...

A Hong Kong road sign giving the same directions twice, in English and in Traditional Chinese.

Using AI in Your Own Language — What the Machine Can Actually See

The same sentence costs seven tokens in English and fifteen in Malay. That gap is usually explained as a money problem;...

A laptop on a steel workbench on a factory mezzanine at night, work gloves and hand tools beside it, machine shop equipment out of focus below

The Best Forward Deployed Engineers May Not Be Engineers

An AI practitioner in Beijing argues that the best Forward Deployed Engineers he has worked with were not computer scien...

A darkened server hall at night, rows of cabinets receding down a concrete aisle with status lights glowing faintly.

Where Does My Data Actually Go?

"Do you use my data?" is two questions wearing one coat. Training asks whether your text enters a future model and is us...

An old hardback book lying open, its thin pages caught mid-turn in warm light.

Why It Confidently Makes Things Up

We asked two AI models for five peer-reviewed studies on an obscure topic, with DOIs. One produced five — authors, journ...

The wooden drawers of an aged library card catalogue with brass fittings.

MCP, RAG, Agents, Skills: The New AI Vocabulary in Plain English

Somebody says the agent will use MCP to hit the connector, then RAG over the docs, and the skill handles the rest. Every...

Rows of set metal letterpress type, the letters mirror-reversed as they are on real printing sorts.

Tokens and Context Windows, Explained From Zero

You are billed in a unit nobody explained. A token is a countable stand-in for a chunk of text — the word is borrowed fr...

A printed invoice on a desk under lamplight, its line items running off the bottom of the page.

What an LLM Actually Costs You

The rate per million tokens is the one number you cannot change, and the smallest part of the bill. Measured on 102 para...

A wall of stacked shipping containers seen flat-on, forming a grid of doors in pale green and grey

Serve an LLM with vLLM on CPU in Docker: Learn the Production Engine Without a GPU (2026)

We ran vLLM v0.25.1's official CPU image in Docker on Apple Silicon, dodged a 10 GB CUDA decoy, survived three traps, an...

Multiple railway tracks with signals and buildings in an urban setting during the day.

Self-Host LiteLLM with Docker: One OpenAI-Compatible Endpoint for Every Model (2026)

We ran LiteLLM v1.93.0 against a local Ollama model in Docker: pinned tags, a 4-line config, token metering, and the wro...

A software developer working at a computer.

How to Run Aider With a Local Ollama Model in Docker (2026)

We ran aider v0.86.2 in Docker against a 986 MB local Qwen model. Same prompt twice: one hallucinated diff, one clean au...

A close-up of a white llama with fluffy fur under a bright blue sky.

How to Self-Host AnythingLLM with Docker and Ollama (2026)

We self-hosted AnythingLLM 1.15.0 with Docker and Ollama, embedded a document over the API, and got cited RAG answers fr...

Colourful building blocks on a wooden floor — Dify assembles LLM apps from visual blocks

Self-Host Dify with Docker Compose: 15 Containers to Your Own LLM App Studio (2026)

We deployed Dify 1.16.0 on Docker Desktop, hit a real port clash, wired DeepSeek, and built a working chatflow — every c...

Rack server rear ports with a patch cable — your private chat stack runs on hardware you control

Run a Private ChatGPT in Docker: Open WebUI + Ollama (2026)

We wired Open WebUI v0.10.2 to Ollama 0.32.1 in two pinned Docker containers, hit one tools-support snag, and caught a t...

Laptop on an office desk — local LLM apps run entirely on your own machine

LM Studio vs GPT4All vs AnythingLLM vs Open WebUI: The Best Local LLM Apps (2026)

We compare LM Studio, GPT4All, AnythingLLM and Open WebUI on licensing, platforms, RAG, multi-user support and telemetry...

A MacBook running a terminal — a local LLM needs nothing else

How to Run a Local LLM on Your Mac with Ollama (2026)

Install Ollama, pull a 1.4GB model, and run a private, offline LLM on any Apple Silicon Mac in ~10 minutes. Every comman...

Server hardware — running open-weight language models on your own machines

The Best Open-Source LLMs You Can Actually Self-Host (2026)

Qwen, Llama, DeepSeek, Mistral, Phi and Gemma compared for self-hosting in 2026 — precise licenses, real hardware needs,...

Working at a laptop — picking a daily AI assistant

ChatGPT vs Claude vs Gemini for Everyday Work (2026)

ChatGPT, Claude and Gemini compared for 2026: real plan prices, default models, work features and usage caps, with a dec...

Connected nodes — choosing an LLM orchestration framework in 2026

LangChain vs LlamaIndex vs LangGraph: Which Orchestration Layer? (2026)

LangChain is now an agent harness on LangGraph, and LlamaIndex moved to Workflows 2.x. We compare all three orchestratio...

Advertisement