i’m not the person you replied to. but a quick google search is just as much effort (on your part) as replying with a sassy “this sounds like a hallucination”. A low value comment in my opinion.
> “AI is already a reality for millions of health workers and patients across the European Region,” said Dr Hans Henri P. Kluge, WHO Regional Director for Europe. “But without clear strategies, data privacy, legal guardrails and investment in AI literacy, we risk deepening inequities rather than reducing them.”
requiring me to explicitly opt-out of something is NOT the same thing as getting my consent. So your argument breaks down there.
You know what getting my consent would look like? Google hosting a form where i can tell them PLEASE SCRAPE MY WEBSITE and include it in your search results. That is what consent looks like.
Google has never asked for my consent. Yet they expect others to behave by different rules.
Now where google may have a reasonable case is that google scrapes with the intention of offering the data “for free”. SerpAPI does not.
It's never been the case that if you put something into public, then you get to reserve your right to refuse public access. Either it's public and strangers can look at it. Or it's private and you need to implement a gate.
are you really asking why someone would like a much better siri?
- truck drivers that are driving for hours.
- commuters driving to work
- ANYONE with a homepod at home that likes to do things hands free (cooking, dishes, etc).
- ANYONE with airpods in their ears that is not in an awkward social setting (bicycle, walking alone on the sidewalk, on a trail, etc)
every one of these interaction modes benefits from a smart siri.
That’s just the tip of the iceberg. Why can’t I have a siri that can intelligently do multi step actions for me? “siri please add milk and eggs to my Target order. Also let my wife know that i’ll pick up the order on my way home from work. Lastly, we’re hosting some friends for dinner this weekend. I’m thinking Italian. Can you suggest 5 recipes i might like? [siri sends me the recipes ASYNC after a web search]”
All of this is TECHNICALLY possible. There’s no reason apple couldn’t build out, or work with, various retailers to create useful MCP-like integrations into siri. Just omit dangerous or destructive actions and require the user to manually confirm or perform those actions. Having an LLM add/remove items in my cart is not dangerous. Importantly, siri should be able to do some tasks for me in the background. Like on my mac…i’m able to launch Cursor and have it work in agent mode to implement some small feature in my project, while i do something else on my computer. Why must i stare at my phone while siri “thinks” and replies with something stupid lol. Similarly, why can’t my phone draft a reply to an email ASYNC and let me review it later at my leisure? Everything about siri is so synchronous. It sucks.
It’s just soooo sooo bad when you consider how good it could be. I think we’re just conditioned to expect it to suck. It doesn’t need to.
I doubt that anyone is actually suggesting that Siri should not be better, but to me I think the issues with it are very much overblown when it does what I actually ask it to do the vast majority of the time since the reality is most of the time what I actually want to ask it to do are basic things.
I have a several homepods, and it does what I ask it to do. This includes being the hub of all of my home automation.
Yes there are areas it can improve but I think the important question is how much use would those things actually get vs making a cool announcement, a fun party trick, and then never used again.
We have also seen the failures that have been done by trying to treat LLM as a magic box that can just do things for you so while these things are "Technically" possible they are far from being reliable.
i’m assuming because of the “web server hosting photos”. Probably Immich if i had to guess?
tailscale is fine if you’re somewhat tech savvy, but it’s annoying to show all your friends and family how to “correctly” access your web server. Too much friction. First download the tailscale app, sign in, blah blah. Then you also are unnecessarily bogging down everyone’s smartphone with a wire guard VPN profile which is…undesirable.
I like tailscale and use it for some stuff. But for web servers that i want my whole family (and some friends) to easily access, a traditional setup makes much more sense. The tradeoff is (obviously) a higher security burden. I protect the web apps in my homelab with SSO (OIDC), among other things.
I prefer to gatekeep "entry points" with Tailscale. A server can have HTTP/S exposed to the world, but its SSH can stay behind Tailscale to enable defense in depth.
Keeping Tailscale as the only security layer will be foolish of course, but keeping the entry points hidden from general internet is a useful additional layer, if you ask me.
As a matter of principle, I like keep the number of open ports to a minimum. Let it be SSH or VPN, it doesn't matter. I have been burned enough times.
I've applied the same principal to my network. Though, I do have plans to re-open some additional ports beyond just SSH / VPN.
Thinking through how I would achieve this introduced me to the concept of a DMZ-zone. The DMZ places publicly accessible services in a highly locked down environment.
DMZ is a very old concept, and applying it is easy when everything is in a single room, connected to a single network, and everything can be isolated there.
When the network is distributed on multiple sites, things get exponentially harder if you don't own a dark fiber from site to site and have essentially a single network.
I personally manage enough servers to scratch that itch, so I yearn for simplicity. If Tailscale gives me that isolation for free (which it does), I'd rather use that for my toy network rather than an elaborate multi-site DMZ setup.
Tip: teach it how to write tests properly. I’ll share what has worked pretty well for me.
Run Cursor in “agent” mode, or create a Codex or Claude Code “unit test” skill. I recommend claude code.
Explain to the LLM that after it creates or modifies a test, it must run the test to confirm it passes. If it fails, it’s not allowed to edit the source code, instead it must determine if there is a bug in the test or the source code. If the test is buggy it should try again, if there is a bug in the source code it should pause, propose a fix, and consult with you on next steps.
The key insight here is you need to tell it that it’s not supposed to randomly edit the source code to make the test pass. I also recommend reviewing the unit tests at a high level, to make sure it didn’t hallucinate.
Example: https://github.com/anthropics/claude-code/issues/1785
reply