I let agents plan a WNBA finals trip (but kept my wallet to myself)

In an experiment to evaluate the latest personal AI agents, the author tasked two advanced bots, Dots from OpenAI and Muse from Meta, with planning a trip for the WNBA Finals, while keeping financial control for themselves. This test highlights the ongoing competition among AI companies to develop versatile digital assistants for everyday tasks, from shopping to travel. The results underscore the gap between current AI capabilities and the level of autonomy users are ready to entrust to these machines, emphasizing the need for these bots to meet what the author calls "The Human Benchmark" to gain broader acceptance.