ChatGPT planned a supposedly 'perfect' trip to Bali — but the hotel address was wrong, a restaurant it recommended as open was permanently closed, and it scheduled transit between destinations in physically impossible time. In Suptravel's test of 50 ChatGPT itineraries, 90% contained errors like these.
1 Answer
Expert: Suptravel research team, Travel technology researchers, Phocuswright & Simon-Kucher data AI travel planning has real appeal: 56% of US travelers used AI to plan trips in 2026 (Phocuswright / Simon-Kucher). But 90% of ChatGPT itineraries in Suptravel's 50-trip test contained concrete errors — wrong hotel addresses, restaurants listed as open when permanently closed, impossible transit timing, and recommendations for attractions in unsafe neighborhoods. Among travelers dissatisfied with AI planning, 52% said the answers were simply incorrect. The right approach: use AI for broad planning scaffolding (destinations, rough day structure, packing lists), then verify every granular detail — addresses, opening hours, transit times — against primary sources before booking. Source: https://suptravel.ai/blog/chatgpt-travel-planning-errors
Your answer
Sign in to verify this AI response.
Don't trust us — or the AI. Ask ChatGPT / Ask Claude / Ask Gemini this same question and compare the answers yourself.
More from this topic
An AI chatbot assured Israeli travelers that their planned route from Thailand to the Philippines via Kuala Lumpur, Malaysia was permissible — despite Malaysia having no diplomatic relations with Israel and Israeli passport holders facing significant restrictions on entry and transit.
AI trip planners confidently produced 2026 itineraries that looked plausible but contained multiple factual errors per trip: hotels listed at wrong addresses or with closed-down operators, opening hours based on 'typical' patterns rather than actual business hours, walking and transit times miscalculated by 30-50%, and visa-on-arrival rules cited as current when the country had changed them 18 months earlier.
Gemini recommended a non-existent wine tasting experience in Bordeaux, gave wrong restaurant hours and menus, and sent tourists to generic tourist spots instead of authentic local food destinations. When asked for localized food recommendations, the AI could not find the eat-in market equivalent of Bordeaux's best spot.