Heard the phrase “if someone wins the lottery” used today to describe a teammate leaving a team. I much prefer this to the more morbid alternatives.
I tried gpt-engineer today. I liked the approach and the setup instructions are good. I think I remember needing to use Python 3.11 instead of 3.8 that I was running, but beyond that the readme instructions we on point.
Process
You start by creating a project folder with a plaintext prompt. You start the script and point it at your project folder. The program reads your prompt then uses the LM to ask clarifying questions. The clarifying questions seem pretty effective. If you answer more than of one of the predetermined questions at once, the program seems to recognizes that and removes it from the list. Finally, it creates an actual project, with source code, pretty consistently (3/3 times I tried). I used it to try and create a 1-player Scattergories CLI game or something close.
Results
Unfortunately, for me, the program didn’t write code that worked in a meaningful sense.
The outputted code is more of a scaffold or an outline of what the project could look like, not having made many meaningful decisions about the structure beyond what you specify.
The somehwat similar project, Auto-GPT, arguably struggles in the opposite direction (as I used it) – researching too much and looping forever.
Gpt-engineer has found another performance pocket, where it consistently, meaningfully outputs something after asking a small number of questions.
As always, I’m on the look out for applications of this agentic tech.