I let agents plan a WNBA finals trip (but kept my wallet to myself)
We put OpenAI's Dots and Meta's Muse to the test.
TL;DR
- OpenAI's Dots and Meta's Muse were tested on their ability to plan a WNBA Finals trip, organize a watch party, and create souvenir programs.
- Both AI agents successfully identified complex issues like rescheduled games and unavailable public ticket sales.
- The agents showed creativity in generating detailed plans but required human editing for accuracy and aesthetics.
- When it came to making purchases, Dots was more effective by directing the user to a pre-configured app, while Muse encountered difficulties.
- The author remains hesitant to grant AI agents full access to financial accounts and decision-making power due to trust concerns.