Generative AI refers to artificial intelligence systems that use deep learning to create new content, such as text, images, or audio.
AI systems are trained on vast amounts of existing information. With additional training and configuration, they can then use what they learned to create new things that seem human-made. The AI model uses its vast mental library to combine and rearrange the knowledge in creative ways.
For example:
- A text-generating AI can write stories, articles, or answer questions.
- An image-generating AI can create new pictures based on text descriptions.
- A music-generating AI can compose new songs in various styles.
These AI models don't simply copy existing work. They understand patterns and concepts, allowing them to produce original content. However, the quality and accuracy can vary, and human oversight is vital to ensuring quality and accuracy.
ChatGPT is an example of a Large Language Model (LLM) developed by the company OpenAI. Although the field is constantly evolving, other LLMs currently defining the field include Gemini (Google), LLaMA (Meta), Claude (Anthropic), and Grok (X).
ChatGPT stands for Generative Pre-trained Transformer, which actually describes how all Large Language Models work:
- Generative means it can create new content, like text or code.
- Pre-trained means it's learned from a vast amount of existing data.
- Transformer refers to the specific type of AI architecture it uses.
Large Language Models (LLMs) are a type of foundational model specifically trained to understand and generate human-like text, answer questions, and perform various language-related tasks.
When you think of AI, you are most likely thinking of a Large Language Model (LLM).
The best way to talk to AI is to have a conversation. Remember, AI is not a search engine! It’s more powerful and conversant, and it allows you to iterate and build on what you’ve asked. For example, with Google you might have searched “garden vegetables that grow in New Hampshire,” whereas with AI you could describe where you live, what the climate is like, if your yard is prone to flooding or drought, what you prefer to eat, and how much time you have to dedicate to gardening. AI works best when you view it as a thought partner and pose a back-and-forth dialogue that helps elevate your work and ideas, not use it to replace learning or critical thinking.
The art of talking to AI is called prompt engineering. While you can always return to the idea of simply having a conversation, a well-crafted prompt can drastically improve the quality and relevance of AI-generated content, reducing frustration and saving time.
To learn more about prompt engineering, check out Prompt Engineering Basics.
