We have people on the team that are android users. I just meant that I don't want to evaluate whether it feels "native" as I personally am not an Android user.
You just install it on your phone and use the app.
Maintainability concerns are entirely overblown by people who don't use agentic AI to develop large mobile apps, but anyway give their opinion as if they had that experience.
I put in a few hundred hours, and I reached the same conclusion as Shopify. With reviews from other models and then a manual QA pass the result is fully usable.
I work as a professional app developer. And I find this take to be naive.
Most of the time when I review code from AI, there is always something to improve.
It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.
The maintenance is not only the burden on the human and LLM. With too many moving parts, it becomes harder and harder to build and verify the correctness of future features. Yes you can write test for this and that, but it didn’t need to exist in the first place.
The second problem is correctness issues. Especially the edge cases. You cannot just manually test out a race condition on a phone! Sometimes it happens! Sometimes it doesn’t! If it leads to a visible signal like a crash, then yes, you can try to reproduce it. But there are a lot of these that are “silent” and would just lead to bad experiences.
We already had a software quality crisis! And I think such views only exacerbate the situation! Quality matters!
And this is not an anti-AI stance. I vibe code personal projects where I don’t even look at the code. But when I use AI as a professional engineer, I act like a professional. Because these products do have an impact on people’s lives.
All true (and thanks for posting a concrete example rather than "LLMS suck"). But my take is that none of this is much different than before times when I had teams of developers creating applications. They would often make similar mistakes which I would either need to catch or which would flush out in the field. Where it seems that LLMs are not excellent is where the person driving it is also the senior domain expert so can immediately spot pitfalls. But typically using humans to develop software this was really not often the case. Those people get promoted so they're no longer cutting the code. Under that scenario (replacing subordinate humans) I find the current models are either on-par or somewhat better (specifically because the models can also act like a peer senior dev, discussing approach options etc).
> It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.
I understand this, but I just can't bring myself to care. I've been doing professional software work for almost two decades. These sorts of improvements/time savers are great without AI. With AI? Whatever. It's fine.
When the underlying lib has an issue, it'll be quicker to debug with the whole thing in context.
So you don't use agentic AI to develop a large mobile app and you think my take is naive?
I also used to work full time as a Android developer for five years, and I'm pretty sure I know better than you about the quality of my app that I work on everyday.
Same result here just using plain Opus 4.8+. I had a web ap with a PWA approach. Now I have an iOS app written in Swift/SwiftUI and an Android app in Kotlin in the appstores. I do not know how to code a single line of Swift or Kotlin. You just test the app and iterate with the AI over it until it is stable and does what it should.
I have been getting these comments often here, including concerns about my non existent backend's security.
Last time, when I pointed out that the attack surface for mobile apps is typically very small, some users started to talk about zero day vulnerabilities in the OS's media handling, as if it was a concern for my app implementation.
Are there cybersecurity concerns in the frontend? I would have thought you have to assume the client is untrusted and only do security work on the backend
No, they said they don't use android so don't know the native UX. You can test your app on the platform and confirm that the functionality all works, but how well it adheres to the platform's design language is subjective and hard to say if you aren't used to the platform.
That's a recipe for regressions as the amount of surface you have to cover with "just...use the app" gets bigger and bigger.
You can write more automation to test it. But that's also how you end up with ever-growing test run times.
There are much better ways that aren't just "throw out the LLM" either. You just need to be more focused on throughput. Requiring manual validation can pretty rapidly require more hours than just sanity-checking code by hand, even (and I'm not advocating that for every use case, either.)
I can't afford manual QA passes if I'm gonna go as quickly as I want to.
I am using Gemini as well as Opus on a somewhat small project in React Native and I can not imagine this thing being able to build the whole thing on its own without it being a dumbpster fire.
Can you share some details of how you work? What models? What harness?
We use CC with Fable(Opus before that) continuously on a rather large project, everything is tested, we maintain high verified test coverage, we ship features x10 faster than when we started(pre Claude-everything era 2-3 years ago). I never worked with RN before and I ship features now. LLMs allowed us to find issues within RN itself, that thanks to some patches, improved lower end Android experience by a lot. We just use all the Claude defaults with claude.md that evolved over last year.
I use Codex and Claude Code desktop apps. I generally use only the SOTA, now Astra and Fable 5.1, Opus 5 when Fable runs out.
I don't know if Gemini is suitable.
I had few issues with my native iOS app, the results are just decent after a few iterations, the models do what I ask them to do. Where do you see the problem?
The LOC for my app is now at almost 200k + 110k lines of test code.
Seriously! What a bonkers thing to claim. "I had codex use maestro so I assume it made Android work well and idiomatically".
It's a fine project to do but clearly they put zero value on being familiar with the project's codebase/stack and ecosystem, which makes me feel fear in my heart when I imagine the first "production is down" page coming in. I already hated mobile because it's so much harder to maintain than web (and I don't do any spyware or IAP so no benefits for me there); this yolo approach would give me constant dread.
It shows that at least some software development is moving away from code and to product management instead. I'm not passing judgement on that; I actually think that's great for a lot of software. It is interesting to see the shift happening though and will be fun to see if the general quality of software noticeably changes over the next few years.
> It's a fine project to do but clearly they put zero value on being familiar with the project's codebase/stack and ecosystem,
As much as I dislike it, I think that's the future of _all_ non-critical software (think social media, crms, CI, food delivery etc). Leadership in many companies is explicitly asking employees to have multiple agents running through the day and that will lead to this.
Read this for example: https://www.uber.com/in/en/blog/efficient-software-factory/ . A very useful system, I am sure. But when you have AI at every layer from code to review to triaging, rest assured AI is the only know who knows your system. And you better hope it's not telling you that something is load bearing during an incident.
I answered elsewhere that I don’t personally use Android phones but we have people on our team that do. Which is why I don’t want to personally claim that it feels native.
But yes we are having real Android users test it.
So it’s quite the contrary. I care MORE what real users say. I can only guarantee that the app does things when I tap. So I’m not trusting the agent on UX, only on functionality. But whether it feels native, I am relying on those users in our team.
I wrote every single line of the react native app we ported, and maintained it for 9 years. So suffice to say, I'm familiar with the code.
But I am going to always prioritize the user experience over a developer (like myself)'s need for satisfaction to see code. And a pure native app is _always_ going to behave better than react native.
> And a pure native app is _always_ going to behave better than react native.
Maybe iOS is better about consistency, but I've used enough horribly made Android apps that I would not expect one that's vibe coded to behave better than a professionally made react native version.
You are familiar with the React Native code, you are not familiar with the Swift or Kotlin code, and likely nobody on your team is, since the AI wrote all of it for you.
Presumably a sarcastic post, but this is actually going to be how things are done soon. I had a box that OOMed and needed to be rebooted every few weeks. It was a disaster recovery standby box so figuring out what was going on never rose to the top of my priority list. So I asked Claude to dig into it (proxying the commands it wanted to run through me) and in an hour it had diagnosed the problem, fixed it, and taught me a bunch about memory usage in our system on modern kernels.
We have people on the team that are android users. I just meant that I don't want to evaluate whether it feels "native" as I personally am not an Android user.
You just install it on your phone and use the app.
Maintainability concerns are entirely overblown by people who don't use agentic AI to develop large mobile apps, but anyway give their opinion as if they had that experience.
I put in a few hundred hours, and I reached the same conclusion as Shopify. With reviews from other models and then a manual QA pass the result is fully usable.
I work as a professional app developer. And I find this take to be naive.
Most of the time when I review code from AI, there is always something to improve.
It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.
The maintenance is not only the burden on the human and LLM. With too many moving parts, it becomes harder and harder to build and verify the correctness of future features. Yes you can write test for this and that, but it didn’t need to exist in the first place.
The second problem is correctness issues. Especially the edge cases. You cannot just manually test out a race condition on a phone! Sometimes it happens! Sometimes it doesn’t! If it leads to a visible signal like a crash, then yes, you can try to reproduce it. But there are a lot of these that are “silent” and would just lead to bad experiences.
We already had a software quality crisis! And I think such views only exacerbate the situation! Quality matters!
And this is not an anti-AI stance. I vibe code personal projects where I don’t even look at the code. But when I use AI as a professional engineer, I act like a professional. Because these products do have an impact on people’s lives.
All true (and thanks for posting a concrete example rather than "LLMS suck"). But my take is that none of this is much different than before times when I had teams of developers creating applications. They would often make similar mistakes which I would either need to catch or which would flush out in the field. Where it seems that LLMs are not excellent is where the person driving it is also the senior domain expert so can immediately spot pitfalls. But typically using humans to develop software this was really not often the case. Those people get promoted so they're no longer cutting the code. Under that scenario (replacing subordinate humans) I find the current models are either on-par or somewhat better (specifically because the models can also act like a peer senior dev, discussing approach options etc).
1 reply →
> It’s either a maintenance issue. e.g., Opus recommended and implemented a fix for a database corruption crash. This was ~400 lines of code with many moving parts. I reviewed, and found out Android Room library already handles this recovery case, and all I needed was a 10 liner PR that catches this exception and ignores it.
I understand this, but I just can't bring myself to care. I've been doing professional software work for almost two decades. These sorts of improvements/time savers are great without AI. With AI? Whatever. It's fine.
When the underlying lib has an issue, it'll be quicker to debug with the whole thing in context.
8 replies →
So you don't use agentic AI to develop a large mobile app and you think my take is naive?
I also used to work full time as a Android developer for five years, and I'm pretty sure I know better than you about the quality of my app that I work on everyday.
1 reply →
Same result here just using plain Opus 4.8+. I had a web ap with a PWA approach. Now I have an iOS app written in Swift/SwiftUI and an Android app in Kotlin in the appstores. I do not know how to code a single line of Swift or Kotlin. You just test the app and iterate with the AI over it until it is stable and does what it should.
> I do not know how to code a single line of Swift or Kotlin
sounds like your app is nothing serious
> You just install it on your phone and use the app.
Some people on the cybersecurity side are starting to cry....
I have been getting these comments often here, including concerns about my non existent backend's security.
Last time, when I pointed out that the attack surface for mobile apps is typically very small, some users started to talk about zero day vulnerabilities in the OS's media handling, as if it was a concern for my app implementation.
I found the concerns again wildly overblown.
2 replies →
Are there cybersecurity concerns in the frontend? I would have thought you have to assume the client is untrusted and only do security work on the backend
8 replies →
They better start a proper hydration regime because they'll be crying a lot.
Why? The api has to be secure. Mobile os keeps the app safe. Where is the attack surface?
1 reply →
> You just install it on your phone and use the app.
OP says they don't have an android phone...
No, they said they don't use android so don't know the native UX. You can test your app on the platform and confirm that the functionality all works, but how well it adheres to the platform's design language is subjective and hard to say if you aren't used to the platform.
Android studio has a emulator
1 reply →
I missed that.
I'd order a cheap Android phone to have a device in hand instead of working only with the simulator.
1 reply →
That's a recipe for regressions as the amount of surface you have to cover with "just...use the app" gets bigger and bigger.
You can write more automation to test it. But that's also how you end up with ever-growing test run times.
There are much better ways that aren't just "throw out the LLM" either. You just need to be more focused on throughput. Requiring manual validation can pretty rapidly require more hours than just sanity-checking code by hand, even (and I'm not advocating that for every use case, either.)
I can't afford manual QA passes if I'm gonna go as quickly as I want to.
I am using Gemini as well as Opus on a somewhat small project in React Native and I can not imagine this thing being able to build the whole thing on its own without it being a dumbpster fire.
Can you share some details of how you work? What models? What harness?
We use CC with Fable(Opus before that) continuously on a rather large project, everything is tested, we maintain high verified test coverage, we ship features x10 faster than when we started(pre Claude-everything era 2-3 years ago). I never worked with RN before and I ship features now. LLMs allowed us to find issues within RN itself, that thanks to some patches, improved lower end Android experience by a lot. We just use all the Claude defaults with claude.md that evolved over last year.
I use Codex and Claude Code desktop apps. I generally use only the SOTA, now Astra and Fable 5.1, Opus 5 when Fable runs out.
I don't know if Gemini is suitable.
I had few issues with my native iOS app, the results are just decent after a few iterations, the models do what I ask them to do. Where do you see the problem?
The LOC for my app is now at almost 200k + 110k lines of test code.
3 replies →
> Opus
1 reply →
Damn, we really gotta get rid of the vibe coders. Bad things are on the horizon if we keep encouraging these naive habits.
How do you propose getting "rid" of "Vibe coders" (which I'm assuming you're pooling me into?)
2 replies →
Yes, what type of "engineering" is this? "I click the button and I see if it works or not" holy shit.
> You just install it on your phone and use the app.
That‘s how you check functionality but that’s not how you get the bugs in the code.
That's the part covered by the other model's review. That together with manually verifying the functionality results in output that works.
3 replies →
Remember the first step to fixing any problem is admitting you have a problem.
If you are blind, you cant see anything wrong, if you are deaf uou cant hear anything is wrong.
Seriously! What a bonkers thing to claim. "I had codex use maestro so I assume it made Android work well and idiomatically".
It's a fine project to do but clearly they put zero value on being familiar with the project's codebase/stack and ecosystem, which makes me feel fear in my heart when I imagine the first "production is down" page coming in. I already hated mobile because it's so much harder to maintain than web (and I don't do any spyware or IAP so no benefits for me there); this yolo approach would give me constant dread.
It shows that at least some software development is moving away from code and to product management instead. I'm not passing judgement on that; I actually think that's great for a lot of software. It is interesting to see the shift happening though and will be fun to see if the general quality of software noticeably changes over the next few years.
> It's a fine project to do but clearly they put zero value on being familiar with the project's codebase/stack and ecosystem,
As much as I dislike it, I think that's the future of _all_ non-critical software (think social media, crms, CI, food delivery etc). Leadership in many companies is explicitly asking employees to have multiple agents running through the day and that will lead to this.
Read this for example: https://www.uber.com/in/en/blog/efficient-software-factory/ . A very useful system, I am sure. But when you have AI at every layer from code to review to triaging, rest assured AI is the only know who knows your system. And you better hope it's not telling you that something is load bearing during an incident.
I answered elsewhere that I don’t personally use Android phones but we have people on our team that do. Which is why I don’t want to personally claim that it feels native.
But yes we are having real Android users test it.
So it’s quite the contrary. I care MORE what real users say. I can only guarantee that the app does things when I tap. So I’m not trusting the agent on UX, only on functionality. But whether it feels native, I am relying on those users in our team.
That's much better than my original, perhaps unfair, read. Thanks for the additional info.
I still would feel scared operating an established product off a newly changed stack the team isn't familiar with though.
> this yolo approach would give me constant dread.
When you’re completely ignorant, there’s nothing to be afraid of.
I wrote every single line of the react native app we ported, and maintained it for 9 years. So suffice to say, I'm familiar with the code.
But I am going to always prioritize the user experience over a developer (like myself)'s need for satisfaction to see code. And a pure native app is _always_ going to behave better than react native.
This gives me a chance to do that.
> And a pure native app is _always_ going to behave better than react native.
Maybe iOS is better about consistency, but I've used enough horribly made Android apps that I would not expect one that's vibe coded to behave better than a professionally made react native version.
1 reply →
>So suffice to say, I'm familiar with the code.
You are familiar with the React Native code, you are not familiar with the Swift or Kotlin code, and likely nobody on your team is, since the AI wrote all of it for you.
First “production is down” page means you just tell codex production is down and to fix it.
Presumably a sarcastic post, but this is actually going to be how things are done soon. I had a box that OOMed and needed to be rebooted every few weeks. It was a disaster recovery standby box so figuring out what was going on never rose to the top of my priority list. So I asked Claude to dig into it (proxying the commands it wanted to run through me) and in an hour it had diagnosed the problem, fixed it, and taught me a bunch about memory usage in our system on modern kernels.
3 replies →
[dead]
ITT: people dealing with realities.
Remember Chinese accounts on US Facebook say data centers are bad.