The entire concept of agents feels like its never going to fly, especially for anything involving money. I am not going to tell and AI I want to bake a cake and trust that will find the correct ingredients at the right price and the door dash them to me.
“…for multi-step tasks”
It’s about Agents, which implies multi step as those are meant to execute a series of tasks opposed to studies looking at base LLM model performance.
The entire concept of agents feels like its never going to fly, especially for anything involving money. I am not going to tell and AI I want to bake a cake and trust that will find the correct ingredients at the right price and the door dash them to me.