This is the typical thinking of the toolmaker. It is not useful in markets. Apple is not in the business of engineering software, their in the business of consumer hardware.

Even more so, having retired themselves from server and workstation market.

Are there more powerful workstations than a maxed out Mac Studio?

First of all, not all workstations are alike.

A maxed out Mac Studio does very little for audio processing, and the custom audio cards that get used in the field.

Second to do the same as many users do with graphics cards configurations, one gets into gimmicks like external eGPU adaptors.

Third, Metal has not much adoption among visualisation software.

Finally, a Mac Studio can only be maxed out once during its lifetime.

Granted, I feel this is true re my non-Mac computers. You think you can max it out at first, but then there's new interfaces, RAM standards, etc

This is apologia. There is a mile between being stuck with 16GB of ram vs on DDR5 or even DDR5. The analogy is absurd.

I'm just saying...between my sandy bridge to the current box, when I looked either having to search for older components vs. just building something new, it was always just easier to build something new. Of course this was when prices were "normal" vs. today....

What is with the website though? Rubbish scrolling. Junky rendering with artifacts if you scroll fast.

Notion is a "knowledge database" with awful performance and jank, that some people have decided sounded like a perfect place to host their blog for whatever reason. But these shared pages been as buggy as the first time I saw them years ago, not sure what they're doing.

Yes, scrolling with the arrow keys does nothing for several presses, then jumps, then acts normally, then jumps again. Really stupid and annoying.

Also, Alt-Left Arrow doesn't return me to the previous page (Hacker News) and I have to use my mouse.

sorry, its a notion not a real site.

You should use my model then, I spent about 30$ in electricity and used my existing RTX4090. It is not very good, but can you compare it with others really? You can use this service via a private API with a VPN, email me your credit card details for access.

This is the most naive take on security ever. For the backend, you assume your client is compromised, but you still don't want to allow your client to be compromised.

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?

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.

what in the gobbledygook is this

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.

> Opus

> 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.

I hate software engineering now.

I was surprised by your comments and then you do Rust to be called via Java or Kotlin and Swift?

What does your app do?

Yes uniffi created swift and kotlin bindings. The app I did with this is just a sudoku game https://www.puzzlesight.com . Before AI I would have reached for something like Flutter to avoid doing all work twice but with AI doing two apps makes more sense.

Okay, makes sense, the whole thing looks and screams vibe coded. On a beefy machine, navigating between your website pages takes 2-3 seconds. So still a long way to go with AI.

Interesting, it's instant on mine. The landing page is just Astro with cloudflare in front of it, the origin server is a hetzner box in Germany though.

Codex with what model?

I think probably GPT 5.5, or 5.6 Sol - it was ~ 2 months ago.

Each time I get access to a new model, I do two things on all our active codebases:

- Security review of all the code and vulnerabilities (new models will find new stuff)

- Code review of test suite quality, and idiomatic patterns/code for the language of that codebase.

And in the case of swift and kotlin, it's even more important that an agent helps me with the code quality since I don't know what "idiomatic" swift or kotlin looks like, the way I do with JS, Elixir, C#, Ruby, etc.

Do you have good prompts to do both?

Sounds like preference. I think it looks beautiful personally.

Everything is a preference. You should stop thinking!

Did you look through the accomplishments? I don't mean to be crass but I like a bit of weight for "accomplished".

I mean, the American Express office looks like a track stop or mall you will find along the highway.

You should really go visit the musical instrument museum if you ever have the opportunity. Just the shortlist of his stuff is pretty objectively impressive, dunno maybe I'm replying to some secret famous person's account shrug.

The will to do and the power to do does not mean well to do.