Yeah this sounds REAL off.

Argh, okay gotcha. Someone needs to start a Framework, but for IoT devices. This is bullshit lol

I do understand what you mean, but I think you’re probably significantly overestimating the difficulty of using the tool. One of its major strengths is its ability to just understand you, like you’d talk to anyone human, with the benefit that you can even instruct it to use a style you prefer. Just say “I’d like your answer to be terse, let’s see if we’re on the right track before getting into details”. Just as an example.

With all that said you know what you want and need better than anyone else, that’s all I’ve got to say on it, cheers!

Just throwing this out there, but the problem you’re describing sounds like a good fit for an LLM I’ve been using for similar purposes, Claude.

I’ve found it to be really good at helping me slog through what would be a burdensome and wasteful amount of reading, in order to answer specific questions OR to get a baseline understanding of a thing.

It’s a bit hard to know how much value comes from my engineering background and my tendency to “know what I don’t know” and thereby ask focused questions, but it’s definitely worth a shot. I have found it to be surprisingly sophisticated and much better than slogging through the wasteland of bad search results + too much unrelated but real info.

A topic like this where there’s a tremendous amount of legit docs, articles, and forum activity - it’s really the exact use case where it’s very difficult for a human, and very easy for an LLM to effectively digest that info.

Some caveats I’ve noticed:

• it sometimes is overly agreeable / “friendly” when it should be more direct
• it does sometimes hallucinate or say BS with casual confidence, which sucks because the more you need the info the less well you can spot that. It hasn’t hampered usefulness too much for me, but then again I’m usually able to spot the mistakes even in ~unfamiliar subjects
• they’ve moved the free tier back to a less capable model at the moment…most of my good experiences are with Claude 3.5 Sonnet, but Claude 3 Haiku (present free tier) is still good

If you’re really curious but the volume of reading and documentation to get started is presenting a big barrier, try using Claude to see how quickly you might be able to clear that obstacle. It’s been removing those exact barriers for me very effectively lately.

Edit to add: a particularly useful way I can imagine folks in your shoes using this - as a “companion” while you try to follow a guide in an article somewhere. It can answer questions about terms you don’t understand, even reasoning behind doing certain steps or what to do if it goes wrong. In fact, you could almost certainly just feed it the written procedure itself (telling it that you’re doing so) and really get it to reason about the process with you. Just help get you through whatever implementation.

Argh, this is exactly the scenario that I’ve anticipated and has kept me away from similar (home automation as well).

That’s what I want, high reliability, local only storage, remote view of some kind, and minimal (ongoing) fuss. Sounds like you did not quite land on that if the thing you bought grosses you out? Or do you mean something different?

You’re right, but I will say the federal govt has a sometimes magic way of greasing certain wheels and getting things done in a hurry, if the right person is pushing on it.

Lol ah yes, the “fork me daddy!” camp weighing in

When did they add blackjack and hookers?! That’s a hell of a feature update

That’s definitely part of the problem. I had an incident recently where an older family member had a minor panic. Because I left my (mfg in 2006!!) vehicle running in the driveway while I ran inside. During the day. In a very safe suburban neighborhood. Just a flat out absurd concern and she leapt right to it, instantly. She’s always been concerned, she’s a grandma, but she wasn’t pointlessly terrified like this years ago.

I think many of us don’t realize how badly this irrational fear has taken hold, or maybe I should say how effectively this irrational fear has been deployed. Otherwise ~reasonable people are walking around thinking the worst is going to happen everywhere at all times, based on absolutely nothing - worse than nothing, it’s based on weaponized deception.

Well, fair enough, folks seem to agree with you and that commenter. I’m not being deliberately uncharitable, “avoid AI at all costs” seems both poorly defined and hyperbolic to me, even given the context. Scams and inaccuracy are a problem in lots of situations, Google search results have been getting increasingly bad to the point of unusable for a while now (I’d argue long before LLM saturation), and I’ve personally been getting mileage with some LLMs, already at kind of an early stage, over wading through every crappy search result.

I wouldn’t call myself an enthusiast or on the hype train, I work in the industry. But it’s clearly useful, while clearly having many tradeoffs (energy use maybe much worse than inaccuracy / scam potential), and “avoid at all cost” is silly to me. But cheers, happy to simply disagree!

Gotta tell you, you made a fairly extreme pronouncement against a very general term / idea with this:

“AI” should be avoided at all cost

Do you realize how ridiculous this sounds? It sounds, to me, like this - “Vague idea I poorly understand (‘AI’) should be ‘avoided’ (???) with disregard for any negative consequences, without considering them at all”

Cool take you’ve got?

Edit to add: whoops! Just realized the community I’m in. Carry on, didn’t mean to come to the precise wrong place to make this argument lol.

I’m becoming more aware of this lately too. Just realizing that Amazon for example has almost negative quality control, in the sense that a counterfeit product from one supplier just gets lumped in with the real ones from other suppliers, and then they sell them having lost the knowledge of who supplied the counterfeit.

And I know no one is checking for flammability of kids’ clothing / items. So I mean, who’s to say stuff made with lead or whatever the fuck else isn’t just getting hucked on down the line too?

Got any rules of thumb or heuristics you’re using? So far all I’ve really got is “nothing for kids from a store without a physical location in my country”. Just basing that on the fact there will at least be someone to sue, which usually encourages better behavior. I also generally avoid the “I can’t believe this is so cheap” products (outside legit sales) because usually something important is getting squeezed somewhere, given the already generally oversquoze situation that is “the market”.

Well said.

Hmm, yes, you’re onto something. I think we’ve sniffed out a very elaborate DnD campaign…in progress!

Exciting times.

Well, I’ll be!

I’m assuming a dice game based around the number 10 most likely lol, but it is possible (and fun to imagine) that maybe rampant tennis enthusiasm needed to be quelled :) Weirder things have happened. Like a town dancing themselves to death.

an exercise in precision engineering with wood

With wood, an hilariously imprecise material (for anyone who doesn’t know). It refuses precision on principle first, and then just on occasion, at every opportunity later.

That delicious (infuriating) imprecision is probably why it can sound so frickin great, though, so…

All I’m getting from this is that something called “tenya” (?) is probably really fun. And now I’m annoyed I’ve never gotten to play!

E: oh maybe just “tens”. Screw it, whatever it is, deal me in lol

Must be satisfying, having the pond you built part of the experience too. I’m just stumbling into the realization that I’m probably going to be in one place for a long time, for the first time, and if my luck continues the WFH will too. In other words I’m realizing I need to widen my scope for how to enjoy my home, to a longer term and to things like that.

Bro.