I did a quick experiment having #GPT chat with itself as Alice and Bob…
At each step, agent Alice answers agent Bob (and vice versa) along with the reinjection of recent context.
I made the discussion start by questionning about the need to regulate AI Large Language Models:
Video excerpt below + thread…
Interestingly in only a few hours, the discussion progressively moved from how to choose an agency that could study the initial question, to health and fitness , and progressively to discussing tastes about… Pizzas.
Quite fascinating, and shows the huge potential of autonomous AI agents.
Where will that lead to?