Even if you disclose to the buyer that it's counterfeit, it's _still_ illegal. You can't just use someone else's name, logo, or protected designs without authorization.

In fact, it's so severe, you can face >= 10 yrs in Federal PMIA prison and owe fines up to $2M — just for the first offense.

Honestly, I initially regretted posting my comment because besides a native iPhone app, I've never built GUI software. I did no research of my one and asked a very open-ended question and felt intellectually dishonest and lazy, and almost deleted it.

I'm so glad I didn't.

This comment is one of the most information-dense helpful resources I've read in a long time (and such a welcome reprieve from the "slop"), that anything I did to contribute to its existence was worth it.

Thank you so much for writing this, and I strongly recommend you post this somewhere very public — on your _beautiful_ personal site at the very least, and I'll do my best to spread it around. I've only built an exquisitely designed iPhone app, as the sole eng alongside a great designer, and barely considered anything but native because our brand was very high-end in the startup-of-a-lifetime great way, and we wouldn't settle for anything else.

But especially with Agentic AI, I could imagine some scenarios where being able to run the guts of your editor out of process, e.g. on a cloud box or even a local docker container, being pretty advantageous.

This is how Claude Code GUI works but to be fair that’s less of an editor.

Pardon the snark, but they literally wrote an article [1] about giving up on code reviews because they push 30k _changes_ (I assume that means commits, but they don’t clarify), and were bottlenecked on reviews.

Instead, they claim to just review the _intent_ of the PR and presume correctness will be caught by more AI.

To me, the more absurd part is that they’re pushing that much code.

To put it in perspective:

    Software     # Commits     Equiv. Time
    --—-----     ---------    -----------
    Nginx            8,758              7h
    uv              11,081              9h
    Vim             24,608             20h
    Go              67,914            2.3d
    Git             82,513            2.8d
    VS Code        168,140            5.6d
    Emacs          183,611            6.1d
    Rust           343,063           11.4d

It generated some interesting discussions here on hacker news [2] [3].

1: https://www.anthropic.com/engineering/redesigning-source-con...

2: https://news.ycombinator.com/item?id=50073633

3: https://news.ycombinator.com/item?id=50118863

FYI: The last is a blog post at simonwilliamson.net about the source post, which was flagged appropriately, but I left since it had a few dozen comments as well.

1: https://microsoft.github.io/language-server-protocol/

If I were to build an editor, I’d want the GUI platform-native so would probably go straight for Xcode and Swift.

If I had a strong aversion to Swift, I might consider a hybrid design where the UI is Swift and write a backend in a modern, fast language I prefer (Go/Rust/C# come to mind, but this isn’t a call-to-arms in the language wars). I believe this could be achieved since LSP works well as a backend server supplying IDE-level niceties, so I could keep most functionality implementations there. I’d have to have a strong reason though since Swift is a fine language, and AI does much of the writing now.

Then again, most devs live on a Mac and deploy to Linux, and are increasingly using Agents which may be better off cloud-hosted or at least sandboxed, so lightweight Swift UI and most logic in a headless cli app could be an interesting design choice.

But the important part to me would be low-bloat and native UI, and I’ve never found cross-platform UI frameworks to hold up in practice — even if only because different OSes necessarily have different ideas of idiomatic design, so you’d either be using least common denominator UI components that feel uncanny, or reimplementing the UI for each platform.

Have you found a language / framework combo that’s fast, fits into the OS well, and is _fun_ to write and use? Or is your idea that separate implementations are now so low cost — who cares — let the AI maintain them?

Legitimately asking in good faith, so please don’t interpret anything as snippy in there — it’s just my understanding of the state of the world. I’d genuinely love to learn about how cross-platform options have expanded if I’m missing something!

Instead, you could make it so anyone who answers after the first person starts out muted and hears a message like: "Uncle Bob's on the line, press 1 to join the call or stay on the line to listen quietly." They could then choose whether or not to join in.

Just a thought! Great idea nonetheless — I'd buy it if I had a valid use case!

Great idea nonetheless though!

* Actionable

* Constructive

* Succinct

* Borne out of relevant experience

And you were sure to thank them for the contribution. This is a model HN comment.

Who cares?

FWIW I use my free iCloud email account with my custom domain since Apple (unlike Google) offers that as a free service. However, I just forward all email to my GMail address and use a custom reply-to in GMail so it _seems_ like I'm using the custom domain in both directions.

Yes, you could ask an LLM to choose between 4 options, and sure have it include a confidence score. But at the end of the day it's still LLM-ing and outputting tokens based on the total probability of the chain of tokens that precedes it to figure out what's most likely to come next.

This taps into a lower level of the model, skipping that tedious token generation step, and exposes you to more raw output from the model, e.g. the actual probabilities involved in answering the question.

It still needs to "think like an LLM" to interpret the question, so it's in the same family, but the thought process gets short-circuited once the question is understood and the raw weights are then extracted as pure, weighted probabilities.

Why would you want to use it? What does it enable beyond a traditional LLM?

(a) It's much more efficient (read: cheaper and faster), and not by a %, but an order of magnitude or two. This makes it practical to be used when an LLM isn't, due to its speed and accuracy, which opens up new use cases.

(b) By getting the raw options and weights, you're not getting the LLM's "spin" on the output, nor hallucination risk — instead, you're using an MRI to pull out exactly what it's thinking before the bullshit verbalization engine kicks in.

Does that help? Please correct me if I'm wrong or went too far in simplifying it, but that's my high-level understanding. I hope this helps.

(4) could be a precursor to a sales pitch for a paid service and (6) obviously has malevolent purposes. But the rest... just people testing agents? Causing mischief?

In other words, the rich don't generally break the law to avoid paying taxes. Rather, they find _legal_ loopholes that work for them, and even create them through lobbying.

Which suggests that legal measures _would_ be likely to work!

On that note, there’s another rule about not commenting on comment votes as well:

>>> Please don't comment about the voting on comments. It never does any good, and it makes boring reading.

https://news.ycombinator.com/newsguidelines.html

FWIW I agree with you, but the rules do seem mostly effective in general.

Anyways, welcome to HN!

Shouldn't someone be looking at some monitoring and see "phillyunsolvedmurders.com," think "hmm that doesn't sound right," and look into it?

I'd actually expect them to engage with, say, 1k websites to voluntarily participate for some remuneration and then restrict the Agents' access to those domains, but apparently I'm crazy.

I’m not taking a side on that debate, just clarifying the relevancy of that quote.