Generative AI Tools
Get Started Using ChatGPT
ChatGPT was asked to explain to a new user how to use ChatGPT for the first time. Here is its answer:
Certainly! Using ChatGPT for the first time is an exciting experience, and understanding the basics will help you make the most of it. Here’s a straightforward guide:
- Access ChatGPT: Usually, you access ChatGPT through a specific platform or website. Once you are there, you will find a chat interface similar to a messaging app.
- Start with a Greeting (Optional): You can begin with a simple hello, though it’s not necessary. ChatGPT is ready to respond to your queries immediately.
- Enter Your Prompt: Type in what you want to know or discuss. This could be a question, a statement, or a request for information or creation. Press ‘Enter’ or the equivalent button to send your message.
- Understanding Prompts: A ‘prompt‘ is your input or instruction to ChatGPT. It tells the AI what you are looking for. Be as clear and specific as possible for the best results.
- Review ChatGPT’s Response: After you submit your prompt, ChatGPT will process it and provide a response. This usually takes just a few seconds.
- Interactive Dialogue: ChatGPT is designed for an interactive experience. You can follow up with more questions, ask for clarifications, or steer the conversation in a new direction based on the response you receive.
- Experiment with Different Types of Queries: ChatGPT can handle a wide range of topics – from answering simple factual questions to more complex requests like explaining concepts, providing recommendations, generating creative content, or even simulating a conversation with a fictional character.
- Respect Boundaries: Remember that there are certain topics and requests ChatGPT is programmed not to engage with, such as generating harmful or inappropriate content.
- Feedback and Corrections: If ChatGPT’s response isn’t quite what you were looking for, you can provide feedback or correct the course of the conversation with more specific prompts.
- End the Session: Once you’re done, you can simply close the chat window or the application. There’s no need for a formal sign-off.
Remember, using ChatGPT is a learning process for both the user and the AI. Do not hesitate to try different approaches in your prompts to see how the responses vary. Enjoy exploring and conversing with ChatGPT!
In November 2023, OpenAI launched ‘GPTs’ which are custom versions of ChatGPT. ChatGPT4 users can create a ‘GPT’ for a specific purpose e.g. create healthy meal recipes without any coding knowledge. Learn more about ‘GPTs’.
Since the launch of Free tier ChatGPT 4o in May 2024, users can now*:
- Browse the web and obtain up-to-date information
- Analyse and extract insights from data (to a portion of users)
- Upload images in your prompts
- Provide support files in your prompts
- Discover and use GPTs
When you ask Free tier ChatGPT 4o a question or give it a prompt to write something, it uses tokens to understand your request and then to create a response. There is a maximum number of tokens Free tier ChatGPT 4o can handle for each interaction. This limit includes both the tokens used to grasp what you are asking (the tokens from your question or prompt) and the tokens it needs to generate an answer.
In simple terms, this means there is a cap on how much text (in terms of words and punctuation) you can give to Free tier ChatGPT 4o in one entry, and also on how long its responses can be. This is like having a word limit for both questions and answers in a conversation. So if you input too many questions or too much text in a prompt, you may exceed the token limit, preventing ChatGPT from processing or fully responding to the request.
*Using ChatGPT’s Free Tier – FAQ
Attribution: ChatGPT4 16/01/2024
Page updated 20th May 2024
In the context of artificial intelligence, especially language models, a prompt is an input given to the model to elicit a response or output.
In the context of ChatGPT and similar language models, "tokens" refer to the pieces of text that the model processes. These can be words, parts of words (like prefixes or suffixes), punctuation marks, or even spaces, depending on the tokenization process used. Tokenization is the first step in processing natural language text, where the input text is split into these manageable units or tokens.
Language models like ChatGPT are trained on massive datasets of text, learning the relationships between tokens to understand and generate human-like text. The number of tokens a model can process in a single prompt or response is often limited due to computational constraints. For example, GPT-3 has a maximum token limit for each input and output sequence, which affects how much text can be processed or generated at one time.
Tokens are crucial for understanding the structure and meaning of language, as they allow the model to analyze text at a granular level. The effectiveness of a language model in understanding and generating coherent, contextually appropriate responses depends significantly on its tokenization process and its ability to manage these tokens efficiently.
