Apple Intelligence broke the ability for Siri to run a shortcut that I use daily. I have a shortcut named, "What's for dinner?" I used to be able to activate Siri and says, "What's for dinner?" and it would set off to my personal mealie server, use an API key to fetch the information, then speak the result. Now, Siri looks through my messages and finds a dinner reservation from OpenTable from months ago and declares that to be fact.

> Now, Siri looks through my messages and finds a dinner reservation from OpenTable from months ago and declares that to be fact.

Settings > Siri > Apps > Messages > "Learn from this App"

Unfortunately Apple makes you toggle this off individually for every single app, seems like an intentional dark pattern that they don't let you toggle off all apps in one go. Also, each iOS updates seems to re-enable Siri for every single app so it doesn't respect your previously disabled apps.

I worked around by adding the shortcut to my control center. Ultimately I'd prefer to have the integrations in place, if Siri ever ends up not sucking.

I'm still using the Dev Kit version that was shipped out before the 3rd Gen launched. tvOS26 was the last version supported so I'll be updating finally. I'd consider 14 years a pretty decent run.

Didn't that one come out in 2015?

Me too! Best $1 I've ever spent

I made a few bucks back off of a game I built for it. So best negative ~$250 I've spent in my case.

I got mine for free!

That's obviously pretty specific to iOS - or MacOS - where there's a single blessed path. Elsewhere, especially in web dev, unless you really don't care about what you get or are making something very simple, you better be ready to provide specifics.

Even still, the majority of things being built on the web perform largely the same if it's being built in Ruby or Rust or Node or Go. Only very niche things, that an LLM would probably fumble over anyway, really benefit from picking the perfect language/framework. The only real advantage to naming your language in the initial prompt is that you can be assured that you'll be able to understand the code when the GPU spins down and output is in front of you.

> you'll be able to understand the code

This should always be a goal. Doing anything major without being able to review manually is just asking for pain over time, or be ready to feed more and more tokens to the fire to reduce sloppiness.

"Make me a ticketing system like Jira"

Now this prompt has huge variety of implementation details. Language? PHP/Ruby/Python/Java/Typescript? In each of them then there are tons of frameworks, templating engines, ORMs, database servers, frontend tooling, bundler, frontend framework alone has several dozen candidates from React, Preact, Vue, Svelte and what not.

So if you really know your craft, you'll already be knowing what specific implementation you need so let us not discount the existing expertise here.

Duo.

I put the text in to gptzero's AI checker and it came back with being Highly Confident it was 100% AI written. I don't think I've ever seen it that confident that the entire thing was AI before.

Claude's style is obvious enough I don't think you really need the checker.

You can tell it's Claude only from reading the H2 tags on the page.

> What happens on October 19

> If you're close to a limit

> What changes and what doesn't

Yes it is, but 100%? Typically someone goes through and touches something to clarify or add a detail.

Been working on a replacement for my Git GUI of choice, Tower, for the last few months. I've been using Tower 2 for almost a decade now, refusing the monthly subscription to upgrade to a fresher version. I'm going to keep mine a one time purchase with support guaranteed for a year. If a major version releases after that, it'll be another perpetual license for the new version. If you want the new features, you can choose to upgrade, if you don't stay on the version you're on until new feature warrant it.

https://www.harborgit.com/

This is very similar to https://battlellmrobots.com that I made, and didn't get any traction on. Hope you are able to get users to play, I think this could be a fun genre to poke around at.

Nice. Yeah I think claude guided everyone to build something similar. "This is a great idea!!, you should totally build it!"

My guess is the reason is, "how much screen would a user be willing to lose to the rear cameras?"

I couch youth sports, and same experience. It's getting better now that the kids are getting older (10-11). But when they were in 1st or 2nd grade, the home schooled kids were so far behind their teammates in social skills.

I only had one on my baseball team in the spring, while he was definitely not on the same level as the rest of the team socially, it could have just been that he is a shy kid by nature.

I've had the complete opposite experience, where adults often tell us they feel like our kids seem much older than their ages.

We lived in different countries where people speak a different language, during their earlier years, though, so maybe that also contributes to it.

It really comes down to the parents, like most things. If parents are heavily engaged, then the kids turn out more well rounded, regardless of where they go to school, public, private, or home.

I can also usually tell just based on the kids if their parents will be helpful or not. If I ask for a parent to help with setting up at the beginning of practice, or if an assistant coach can't make it and I need a hand, the way a kid acts is a pretty good indicator if their parent will get out of their chair on sidelines and come help.

There are outliers, but its a pretty good rule of thumb.

For users, ease of use.

For companies, ease of additional tracking.

It really isn't some _deep_ thing. Users like to be able to quickly access the content they want to consume. Companies want data. Apps fulfill both of these requirements.