Comment by pscanf
6 months ago
> your methodology would seem to be a reasonable approach/response to get the benefits of this and to shield against the detriments
If you're referring to the sandboxing / isolation of each app, I agree. Plus, the user can change the app quite easily, so if when they spot a bug, they can tell the agent to fix it (and cross their fingers!).
> ensure that a human developer understands the code before committing
Just to clarify: for Superego's app there's no human developer oversight, though. At least for the ones the user self-creates. Obviously the user will check that the app they just made works, but they might not spot subtle bugs. I employ some strategies to _decrease the likelihood of bugs_ (I wrote a bit about it here https://pscanf.com/s/351/, if you're interested), but of course only formal verification would ensure there aren't any.
I was referring more to your commentary/explanation about it not being a Vibe-coded app.
Yeah, I can see that one is on their own recognizance when letting an LLM run unsupervised.
Ah yeah, I understand now. And I also agree with the quote then! (Though it does change the nature of the job, and it's not terribly enjoyable...)
Hopefully you can find some way to keep the enjoyment in this.