zsoltkacsandi

I had an incident in prod years ago, that no one was able to solve from my team, and it took days for me to figure out what is happening. It was a tricky one.

For Claude it took 10 minutes to solve it.

What I do is that each of my requirements are captured in a yaml file, with a unique id, with the exact sentence I wrote. Each must be covered/proven at least with one test, a linter checks whether the requirement is covered (test exists annotated with that id), and a test inventory generated from it. Usually I browse and review the test inventory first to see I get what I asked. It does not guarantee that the agent implemented everything correctly, but if I ask another agent to review it and point out the gaps, it produces very good results.

> First let us install other browser engines on iOS, and then we can talk

Just checked in the App Store, I can install Firefox, Opera, Brave, and many many other browsers on my iPhone.

There will be, but the question who will be able to afford it.

It’s like saying that there is no housing crysis in several countries because the market is full of houses, apartments, etc.

No one will use AI products if there won't be consumer products because of RAM shortage.

Or nerfed version of models rolled out gradually.

> I've seen this one a few times lately. People should stop building UIs, nobody wants to interact with a UI. Everyone's app should just be an API that you can use with a chatbot.

Same happened when the first smartphones came out, and everything was about "mobile first". Everyone will use their mobile phones for everything, desktop is dead, every app should be primarily designed for smartphones, everything comes after. Turned out smartphones just another interface that are good for some things, and not good for some other. Same for the "cloud native" movement.

Prevention is not about age related diseases, but early onset cancer, diabetes, high blood pressure caused by alcohol and tobacco use, unhealthy diet, and sedentary lifestyle.

A significant amount of cases could be prevented before they need medical intervention (and put burden on the medical system). There are several researches about this, the number of people with type 2 diabetes doubled in the past decades.

This is why some healthcare systems reward for example doing 10.000 steps a day with lower insurance fees. They recognized they save a huge amount of money if they get people to move.

> The reality is we need more doctors. A lot more.

I think building a better prevention layer is more important.

Don't get me wrong, I agree that we need more doctors (and nurses, and physios, and dietetists, and ...), but it is much easier to scale a good prevention system than the number of workers in healthcare.

That is very well put and summarizes what distinguishes real software development from vibe coding.

No, it’s not. 24 hours is the same as series 11. And you are comparing to series 10, not 11, that already had this improvement. I do not work out 10 hours a day, so that number is literally meaningless/pointless.

I have hearth issues too, and the metrics Apple provides still do not help detecting them. Not to mention that there is no improvement of their high blood pressure detection. So despite the marketing that they have the most accurate sensor, there is no real advancement here.

Disappointing. Instead of making battery life better that would benefit all of the Apple Watch users, here are some random AI features that most of you never gonna usa, and some new colors.