[33a]

For comparison, I asked ChatGPT to build one and here's what I got in one shot:

https://chat.openai.com/share/b4b399ef-1def-4f68-b2f1-8c56ca...

Seems to work correctly, didn't have to change anything in the code.

Like all the other agenty stuff I've seen it's not clear what the fluff adds over just prompting the base model.

[kosh2]

Maybe simply a larger task?

"Write 10 popular mini games"

--> What are those games? 1. Agent --> How does each of them work? 2. Agent --> Write each of those. Agent 3-13

[33a]

I'm just using the examples from the paper. Here's another one:

"Implement a Gomoku game using Python, incorporating an AI opponent with varying difficulty levels."

One shot prompt works fine: https://chat.openai.com/share/4435152f-ba13-45a5-a116-eb4f57...

AFAICT using ChatGPT directly gets you better results with lower cost and less complexity. The "MetaGPT" framework adds bloat and delivers nothing.