AI & LLMs · Beginner
Claude
A large language model built by Anthropic, known for understanding long documents, writing well and writing code. It comes both as a chat assistant on the web and phone, and in a dedicated form for programming.
TL;DRIn 30 seconds
- A large language model made by Anthropic, strongest at long documents, writing and code.
- It's used in two ways: the one you can chat with any time, and the one that edits code inside your editor.
- The same name covers both a model and a tool — work out which one is meant.
OverviewIn detail
Claude is a large language model made by the American company Anthropic — think of it as an AI that can hold a conversation with you and write things for you. Its hallmarks are understanding long documents well, producing steady, dependable text, and being widely recognised as strong at code.
Anthropic was founded by people who came out of OpenAI, and puts AI safety front and centre, stressing that models should be more reliable and less prone to going off the rails. That's why it's often recommended for tasks where care and a low error rate matter, and its manner of speaking is more restrained than some rivals'.
There are two common ways to use it. One is chatting directly in the web or phone app; the other is a dedicated programming-assistant form, where once it's installed you can ask it in everyday language to change code or add features. Many skills are made specifically for that programming form — when a description says it applies there, it means the skill can be loaded and used inside it.
The easy mix-up is taking it and the other product sharing its name to be two companies. Claude is the model itself; the programming assistant is a tool that wraps it up specifically for writing code. And it and ChatGPT are products from two different companies, each with its own style — don't lump them together.
In practice you can treat it as an assistant with strong language ability and a steady manner. For reading long material, writing formal documents and working with code it usually does well; whether to pick it still comes down to price, and to whether it can connect to the tools you already have.
MythsCommon misunderstandings
- ✕Thinking Claude and Claude Code are two companies ✓They are one company's model and tool — the model is the ability, the tool is the shell around it
- ✕Thinking it exists only for writing code ✓Reading long documents, writing and conversation are all everyday uses — code is just one of them
In practiceWhere you will meet it
- Dropping a contract or a paper dozens of pages long into it and having it walk through what each part says
- Using everyday language in your editor to have it change code or add features
- Handing it something you wrote so it can pick out the problems and fix the tone
SummaryThe key points
- A large language model from Anthropic
- Strong at long-document understanding, writing and code
- Built around an emphasis on AI safety, with fairly restrained output
- Besides chatting, it has a dedicated programming-assistant form
FAQ
What does Claude mean?
A large language model made by Anthropic, strongest at long documents, writing and code.It's used in two ways: the one you can chat with any time, and the one that edits code inside your editor.The same name covers both a model and a tool — work out which one is meant.
Where will I run into Claude?
Dropping a contract or a paper dozens of pages long into it and having it walk through what each part says;Using everyday language in your editor to have it change code or add features;Handing it something you wrote so it can pick out the problems and fix the tone。
What do people most often get wrong about Claude?
Thinking Claude and Claude Code are two companies — but They are one company's model and tool — the model is the ability, the tool is the shell around it;Thinking it exists only for writing code — but Reading long documents, writing and conversation are all everyday uses — code is just one of them。
What are the key points about Claude?
A large language model from Anthropic;Strong at long-document understanding, writing and code;Built around an emphasis on AI safety, with fairly restrained output;Besides chatting, it has a dedicated programming-assistant form。
Common pitfalls It is the model; the programming assistant is the tool this company built from it — not two companies, and not two unrelated things.
Entry 4 of 186 · All entries
Keep readingRelated reading
AI Agent
An AI program that sets its own goal, breaks it into steps and calls tools to get the job done. You hand it a task and it works out how to do it — instead of only answering one question at a time.
LLM
A very large program that learned to predict the next piece of text after reading an ocean of it. Whatever you type, it is guessing what is most likely to come next — writing, translating and answering questions are all the same thing used differently.
嵌入(Embedding)
把一段文字换算成一串数字,让电脑能比较哪两句话意思更接近。搜索和知识库能在换了说法时也找对答案,靠的就是它。
Prompt
The message you send to an AI — the instruction or question you give it. How well that passage is written decides whether the answer that comes back is on target.
MCP
A standard interface that lets AI connect to outside tools and data in one uniform way. Build a tool to it once and any AI assistant can call it, saving you from writing a separate integration for each tool.
Workflow
Breaking a job into fixed steps and running them through in order automatically. Once the process is set, one sentence re-runs the whole thing instead of doing it by hand again.
Where to go nextExplore more
Back to the skills themselves
Most of the concepts covered here come from skills that install into your AI client with a single command.