Receive insightful updates directly to your email inbox by subscribing to our weekly newsletters. Stay informed on the latest developments in enterprise AI, data, and security leadership. Join Now
When OpenAI unveiled GPT-5 approximately two weeks ago, CEO Sam Altman claimed it would be their most intelligent, fastest, and most practical model to date. However, instead of receiving accolades, the launch sparked a significant backlash from users, making it one of the most controversial events in the realm of consumer AI.
A new blind testing tool, developed by an anonymous creator, is shedding light on the complexities behind the negative reactions and challenging preconceived notions about how individuals truly interact with advancements in artificial intelligence.
The tool, accessible at gptblindvoting.vercel.app, presents users with pairs of responses to identical prompts without disclosing whether they originated from GPT-5 or its predecessor, GPT-4o. Users are tasked with selecting their preferred response across multiple rounds, receiving a summary afterwards to reveal which model they favored in reality.
The creator, known only as @flowersslop on X, shared, “Some of you asked me about my blind test, so I created a quick website for yall to test 4o against 5 yourself.” The tool has garnered over 213,000 views since its launch last week.
The early results shared by users on social media depict a split reminiscent of the broader controversy. While a slight majority express a preference for GPT-5 based on blind tests, a significant portion still leans towards GPT-4o, indicating that user preference transcends typical technical benchmarks that define AI progress.
