An artificial intelligence model that makes suggestions to another AI can get it to produce results that are as good as if the prompts came from humans. The technique could be used to improve the performance of AIs whose internal workings remain opaque.
Large language models (LLMs) are neural networks that are trained on vast data sets of online text and can produce convincing language. You give the model an input, called a prompt, and it gives you a response. No one knows exactly how these LLMs arrive at the results they do, but by tweaking the prompt, you can sometimes get better results.
For instance, adding the phrase "let's think step-by-step" to prompts seems to make these language models better at solving problems that they tend to struggle with.
Now, Yongchao Zhou at the University of Toronto in Canada and his colleagues have developed a model called Automatic Prompt Engineer (APE) that uses a language model to come up with similar prompts aimed at a desired outcome that appear to be just as effective, or better than, if a human was thinking up the suggestions.
From New Scientist
View Full Article
No entries found