alwillis

Claude Code has output styles; one of the predefined styles is Concise [1].

    Concise: Claude leads with the result, skips preamble and narration, and
    keeps responses short by default, while doing the engineering work as
    thoroughly as in the Default style. When you ask for an explanation or
    more detail, Claude answers in full. Claude always keeps the complete
    content of error reports, security warnings, and confirmations for
    destructive actions. Requires Claude Code v2.1.237 or later.

[1]: https://code.claude.com/docs/en/output-styles

The godfather of AI himself, Geoffrey Hinton, believes LLMs are conscious.

I get it; when Safari was available for Windows, the font rendering was different from the Mac version.

> And I can't test the new version of Safari on my Windows or Linux devices because Safari isn't available for them.

You can download three Linux-compatible WebKit-based browsers from Apple's WebKit page:

Epiphany Technology Preview: https://webkitgtk.org/epiphany-tech-preview

WPE: http://wpewebkit.org/download

WebKitGTK: http://webkitgtk.org/download

>> JXL was dead. Apple is who brought it back to life

> No, it was actually the PDF Association.

The PDF Association didn't adopt JPEG-XL until September 2025. By then, Apple had been shipping JPEG-XL in Safari for two years [1]. So there's that.

[1]: https://webkit.org/blog/14205/news-from-wwdc23-webkit-featur...

> LLMs are also terrible at these new standards. If they even know about them, they often think they're not baseline yet…

It doesn’t have to be that way.

You could create a Skill [1] that tells the agent to use modern css; the newer models like Opus 5 are probably much better with modern css.

Google released a set of skills at I/O called Modern Web Guidance [2] that steer coding agents to use modern css and best practices.

[1]: https://www.skills.sh/paulirish/dotfiles/modern-css

[2]: https://developer.chrome.com/docs/modern-web-guidance/get-st...

> The common advice now is to only use CSS that is supported in the last two major versions of each major browser.

There's a much easier way—Baseline: https://web.dev/baseline

CSS features that have been available for 30 months for Chrome, Edge, Firefox and Safari are "Widely Available" and are safe to use.

Commonly used tools like Browserslist and Stylelint support checking for Baseline compliance.

An excellent list of modern CSS: https://nerdy.dev/cascading-secret-sauce.

There's also https://modern-css.com/.

There's a newer MacDown--MacDown 3000 [1]. It's a universal binary, so it'll keep running once Rosetta goes away.

[1]: https://macdown.app

Feature requests:

* YAML support So many of my markdown files have YAML front matter, it would be nice for Scriptum to render it properly.

* Definition lists MultiMarkdown[1] and Kramdown[2]support definition lists which are pretty useful when authoring markdown

[1]: https://fletcherpenney.net/multimarkdown/

[2]: https://kramdown.gettalong.org

> That would be a very Apple thing to do.

That's something Steve Jobs would have done.

He left in 2019 and formed his own company, that did design work for Apple until 2022.

He "took" several Apple employees with him when he left and there's been a steady stream of Apple employees going to OpenAI.

Ive isn’t responsible for all of them obviously, but the articles about lawsuits says there are 400 former Apple employees at OpenAI.

Definitely not slow.

> I mean, the point stands. The models are beyond expert level in many areas at this point.

It's not that the models aren't smart or whatever; we know they're extremely capable.

There's always going to be value in being able to clearly communicate what you want the model to do, especially when the context is lacking.

> Is this the reason OpenAI decided to steal Apple hardware secrets?

Of course not.

Pretty sure this isn’t the secret Jonny Ive project.

> Every country and group has practiced slavery.

The colonies and, later, the United States didn’t just practice slavery; they industrialized it by transporting by force 12.5 million Africans to the Americas for nearly 250 years.

Even as fortunes were made, that didn’t stop the torture, rape, and brutality of these enslaved people.

Even after the Civil War, the descendants of the former enslaved people had to live under the Apartheid-like system of Jim Crow that lasted for another hundred years until the Civil Rights Act was enacted in 1964 and the Voting Rights Act in 1965.

> I suspect they're subsidizing a lot less than people think.

Agreed.

> Looks like all the reporting about Anthropic trying their earnest to turn a profit this quarter is true.

That's not how any of this works.

Anthropic is playing the long game; they're not going make a short-sighted decision just so they announce a profit for one quarter, which doesn’t mean much because it won’t be a sustainable profit since they're going to need to spend a ton of money on training and compute over the next few months.

That's why they did a G funding round for $14 billion in February and $65 billion in May.

I suspect one reason for switching Fable to API usage for the near future is they don't have enough compute for their enterprise customers and every hobbyist on their $20/month Pro plan, 80% of which don’t need Fable 5 anyway but that won't stop them from using it as much as they can.

We know an exception doesn’t necessarily prove the rule. macOS has always had superior text rendering support since the NeXT days.

SwiftUI is immature but getting better. There have been tons of AppKit apps with excellent text support. Don't know what this guys problem is.

A native macOS app done correctly is superior to a web app in virtually every way. Claude Desktop won't be a best-in-class app if it remains a web app. Simple as that.

> If the purported benefits of agentic-coding systems are real, it should have been trivial for Anthropic to implement a native macOS application, and sell it as a benefit, no?

Absolutely. But there's the support, documentation and testing aspect and how they're setup.

To their credit, OpenAI acquired a team of experienced macOS developers when they bought Sky [1], the basis for the Mac version of Codex. Apple acquired Workflow from the same team years ago, which became Shortcuts, a core part of macOS's automation system.

Anthropic says 80% of their code is written by Claude; the remaining 20% requires some human expertise, especially with platform-specific features.

A native macOS version of Claude Desktop (and therefore Claude Cowork) would be a huge step forward for Anthropic. Hopefully it's a matter of when, not if.

[1]: https://www.macstories.net/news/sky-acquired-by-openai/

> I don’t understand how Gruber can think the ChatGPT app is that good. It’s also…fine,

It's not that ChatGPT is so good; it follows macOS design principles and functionality that have existed for decades. Claude Desktop sometimes does and sometimes doesn’t which can be a frustrating user experience.

It's the Mac version of OpenAI's Codex app where you see the night and day difference between the two.

> I tried using RDFa and liked the property that it was theoretically less redundant, but switched to JSON-LD because it JSON-LD is just easier to get working.

For me, it depends on the project. For personal projects, I tend to use RDFa; otherwise, JSON-LD.

They don't conflict; they were designed to work together. You can have schema.org (in JSON-LD, RDFa, or micro data) on the same page as Dublin Core, etc.

For example, there's no explicit property in schema's Person type [1] for a nickname. But the FOAF standard does [2].

Just add FOAF to the JSON-LD context:

    {
      "@context": {
        "@vocab": "https://schema.org/",
        "foaf": "http://xmlns.com/foaf/0.1/",
        "pronouns": "https://schema.org/pronouns" 
    }

You now use the FOAF nickname property:

    "@type": "Person",
      "givenName": "Timothy",
      "familyName": "Berners-Lee",
      "foaf:nick": "TBL",

You can do the same thing with Dublin Core, DBPedia, etc.

[1]: https://schema.org/Person

[2]: https://xmlns.com/foaf/spec/#term_nick

Check out “Bring an LLM provider to the Foundation Models framework” - https://developer.apple.com/videos/play/wwdc2026/339

> Homebrew is the first thing I install on a new Mac.

Absolutely!

Just a FYI: Bundler now supports cooldown [1].

[1]: "Cool down before you install: give new gems a few days to be vetted" - https://blog.rubygems.org/2026/06/03/cooldown-let-new-gems-b...

> Nothing new about it.

Besides starting at $599 (the Air has mostly been a $999 product; occasionally selling at $799 at Costco), coming in 4 bright colors with matching keyboards, using an A series chip for the first time in a Mac, containing 90% recycled aluminum (the most of any Apple product) and breaking all Mac laptop sales records, there's nothing new about it. /s

The MacBook Neo is a new idea. It’s also a device most Apple skeptics didn’t think was possible.

> Personally, I would want that R&D spend and innovation to go to more sustainable materials, longer lasting devices, and easily repairable parts to extend the devices useful life.

Apple probably leads the industry in sustainability–the MacBook is 60% recycled material.

They’ve been working for years to be carbon neutral by 2030.

Details at https://www.apple.com/environment/