CNN Travel challenged ChatGPT to come up with city guides (www.cnn.com)

CNN Travel recently put OpenAI's ChatGPT to the test by using it to generate tailored city guides for five major cities: Atlanta, Hong Kong, New York, London, and Bangkok. The initiative aimed to explore how well AI can create personalized travel itineraries while accounting for individual preferences and practical travel constraints. The team found that while ChatGPT offered some useful suggestions tailored to specific prompts, it also exhibited notable limitations, such as generating “hallucinations” or inaccuracies about logistics, such as suggesting itineraries involving non-existent transportation options. This exploration is significant for the AI/ML community as it showcases both the potential and current challenges of large language models (LLMs) in the travel and tourism sector. The results emphasized the importance of providing detailed prompts to improve the specificity of the AI's recommendations while also highlighting the need for users to critically evaluate the information provided. As AI tools continue to evolve, their ability to assist in complex, personalized tasks like travel planning will depend on reducing errors and improving contextual understanding, paving the way for more accurate and user-friendly applications in various industries.