In two stages allows you to generate an AI written essay
The following demonstration uses Open AI's GPT-3 language model. It breaks down the task of producing an essay on any given topic into two stages, first creating an essay plan then using this plan to generate the written text.
- Enter a topic in the box below, or select from one of the example topics.
- Click the Analyse button.
- View the generated essay outline.
- If you like the generated essay outline, select 'Generate Essay Text' to create the full AI-generated essay.
More information about this demo
GPT-3, Generative Pre-trained Transformer 3, is an autoregressive language model produced by OpenAI. It uses deep learning to produce what appears to be human-written text. It was trained on 175 billion machine learning parameters. There are four different iterations of GPT-3, Ada, Babbage, Curie and Davinci. Ada is the fastest, most afforable, lowest performing model, and Davinci is the slowest, most expensive, yet highest performing, with Babbage and Curie ranging inbetween. GPT-3 has a three main modes, complete, insert and edit, creating a number of different use cases; the most common being Text Completion. In this example, two stages of commands are passed to the model, the first asks for an essay outline on the user provided topic, this outline is then broken down into individual commands, which asks for a paragraph focused on a stage of the previously generated outline. The more information you provide the tool, the more accurate the response will be.
Things to consider
The tool will generate a different answer each time it is run, so if you don't like a response, rerun the same parameters and get a different essay outline and text. In the case of OpenAI's GPT-3, the LLM was also trained on data gathered prior to 2021, so may not have knowledge of current affairs past that cut off. The results generated may also be used in training future models.