Comment by hattmall
6 days ago
I guess for me the questions is, at what point do you feel it would be reasonable to this without the experts involved in your case?
As an edit, after reading some of the prompts, what is the likelihood that a non-expert could even come up with those prompts?
The really really interesting thing would be if an AI could actually generate the prompts.
(I'm the author of this library -- or, the guy who prompted the AI at least.)
I absolutely would not vibe code an OAuth implementation! Or any other production code at Cloudflare. We've been using more AI internally, but made this rule very clear: the human engineer directing the AI must fully understand and take responsibility for any code which the AI has written.
I do think vibe coding can be really useful in low-stakes environments, though. I vibe-coded an Android app to use as a baby monitor (it just streams audio from a Unifi camera in the kid's room). I had no previous Android experience, and it would have taken me weeks to learn without AI, but it only took a few hours with AI.
I think we are in desperate need of safe vibe coding environments where code runs in a sandbox with security policies that make it impossible to screw up. That would enable a whole lot of people to vibe-code personal apps for personal use cases. It happens I have some background building such platforms...
But those guardrails only really make sense at the application level. At the systems level, I don't think this is possible. AI is not smart enough yet to build systems without serious bugs and security issues. So human experts are still going to be necessary for a while there.
> I think we are in desperate need of safe vibe coding environments where code runs in a sandbox with security policies that make it impossible to screw up.
OpenAI's new Rust version of Codex might be of interest, haven't dived deeper into the codebase but seems they're thinking about sandboxing from the get-go: https://github.com/openai/codex/blob/7896b1089dbf702dd079299...
What tools did you use for the vibe coding an Android app? And was it able to do the UI stuff too?
I've wanted to do this but am not sure how to get started. For example, should I generate a new app in Android Studio and then point Claude Code at it? Or can I ask Claude Code (or another agent) to start it from scratch? (in the past that did not work, but I'm curious if it's just a PEBKAC error)
I used Claude Code. I actually just asked it what tools I needed for a CLI-driven build, and it told me what to install (or even installed it for me in some cases). I basically didn't read any documentation, just asked Claude what I should do.
1 reply →
> I do think vibe coding can be really useful in low-stakes environments, though. I vibe-coded an Android app to use as a baby monitor (it just streams audio from a Unifi camera in the kid's room). I had no previous Android experience, and it would have taken me weeks to learn without AI, but it only took a few hours with AI.
Bro, you're still an engineer at Cloudflare!
One problem I see with "vibe coding" is how it means one thing if Ilya Sutskever says it, and another if a non-tech executive parrots it and imagines "citizens developers" coding their own business apps.
> I guess for me the questions is, at what point do you feel it would be reasonable to this without the experts involved in your case?
I don't know if it was the intent but these kind of questions bother me, the seem to hint at an agenda, "when can I have a farm of idiots with keyboards paid minimum wage churn out products indistinguishable from expertly designed applications".
To me that's the danger of AI, not it's purported intelligence, but our manifested greed.
Yeah, I mean that is definitely the intent of the question and it's absolutely one of the factors that's driving money into AI.
Assisting competent engineers certainly has value, but it's not an easy calculation to assess that value compared to the actual non-subsidized cost of AI's current state.
On the other hand having a farm of idiots, or even no idiots at all, just computers, churning out high quality applications is a completely different value proposition.
Why do you need a non-expert? We built on layers of abstractions, AI will help you at whichever layer you're the "expert" at. Of course you'll need to understand low-level stuff to work on low-level code
i.e. I might not use AI to build an OAuth library, but I might use AI to build a web app (which I am an expert at) that may use an OAuth library Cloudfare developed (which theya are experts at). Trying to make "anyone" code "anything" doesn't seem like the point to me
GP is just quoting the readme, they aren't the author.
My 2 cents:
>I guess for me the questions is, at what point do you feel it would be reasonable to this without the experts involved in your case?
No sooner and no later than we could say the same thing about a junior developer. In essence, if you can't validate the code produced by a LLM then you shouldn't really have been writing that code to begin with.
>The really really interesting thing would be if an AI could actually generate the prompts.
I think you've hit on something that is going underexplored right now in my opinion. Orchestration of AI agents, where a we have a high level planning agent delegating subtasks to more specialized agents to perform them and report back. I think an approach like that could help avoid context saturation for longer tasks. Cline / Aider / Roo Code / etc do something like this with architect mode vs coding mode but I think it can be generalized.