Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A sane but bull case on Clawdbot / OpenClaw

brandon.wang

Post reply on HN
Print view View original

411–420 of 504 posts

Re: A sane but bull case on Clawdbot / OpenClaw

#411

Post by nfw2 »

oersted wrote: post #88
okinok wrote: post #7

>all delegation involves risk. with a human assistant, the risks include: intentional misuse (she could run off with my credit card), accidents (her computer could get stolen), or social engineering (someone could impersonate me and request information from her). One of the differences in risk here would be that I think you got some legal protection if your human assistant misuse it, or it gets stolen. But, with the…

Indeed, even if in principle AI and humans can do similar harm, we have very good mechanisms to make it quite unlikely that a human will do such an act. These disincentives are built upon the fact that humans have physical necessities they need to cover for survival, and they enjoy having those well fulfilled and not worrying about them. Humans also very much like to be free, dislike pain, and want to have a good rep…

On the other hand, other humans may have intrinsic interests outside of your control that may lead them to harm you despite the mechanisms you mentioned, whereas bots by default don't have such motives.

Re: A sane but bull case on Clawdbot / OpenClaw

#412

Post by XorNot »

direwolf20 wrote: post #377
insane_dreamer wrote: post #263

Earlier quoted context omitted.

Yeah, a lot of these AI "uses" feel like solutions looking for a problem. It's the equivalent of me having to press a button on the steering wheel of my Tesla and say "Open Glovebox" and wait 1-2 seconds for the glove box to open (the wonders of technology!) instead of just reaching over and pressing a button to open the glovebox instantly (a button that Tesla removed because "voice-operated controls are cool!"). Or…

Tesla removed all the buttons because separately designed buttons are expensive. The glovebox button is different from the wiper button. Touchscreens are cheap because you only need one variety.

The problem is Tesla is a quasi-premium brand, so killing features for cost which cause annoyance is a terrible look.

But also frankly I somewhat question what this could possibly be saving them: their model range is very limited.

Re: A sane but bull case on Clawdbot / OpenClaw

#413

Post by nfw2 »

PurpleRamen wrote: post #122
zozbot234 wrote: post #30

Earlier quoted context omitted.

It's set up to wake up periodically and work autonomously for you based on the broad instructions it's been given. Compared to the usual coding agent workloads, this makes it a lot more "assistant"-like.

So people are hyped because they don't know cron?

It is combination of:

- Cron-style heartbeat manager

- Easy customization with markdown only

- Good out-of-box memory management that just works

- Good set of tools out-of-box that just work

Like Jack Dorsey said about project success, limit number of details and make those details perfect

Re: A sane but bull case on Clawdbot / OpenClaw

#415

Post by thinking_cactus »

cyanydeez wrote: post #399
hmokiguess wrote: post #396

I feel like for some people these chatbots are sort of becoming something like their "service animals". They fill a void, a gap, some core loneliness, reduce anxiety from dealing with the uncertainty and challenges of life. As others mentioned here, a lot of the value add from his workflow is just relocating things from one place to another and micro optimizing.

Ever since the Matrix, id assumed its more likely humans will put themselves in the Matrix than theyd actually explore the universe. Theyre equally complex challenges but the physics of large time/space are just outside human patience. Also, if the neo nazis are in charge another round of inhumane testing will occur.

I get why it is romantic (like the "next thing" after other human discoveries), but I don't think "exploring the universe" is that philosophically interesting?

Think about the case you had

(1) A completely environmentally-resistant suit (so you can stand on the surface of basically any planet)

(2) A teleporter to take you absolutely anywhere instantly

Still in this case, you'd probably spend a while visiting new planets, but eventually it would be kind of an exercise in geology. There would surely be some amazing sights like huge canyons and whatnot. But I can't help but think it would be eventually boring without human culture (or all sorts of life) surrounding it.

I think literally exploring art and culture (including games, sports and intellectual pursuits, science, etc.) is much more interesting than exploring the universe, it's a shame this isn't as culturally recognized (so we didn't have to be so obsessed with having more and more stuff to go somewhere that isn't just right here on Earth).

Even if you brought human life and culture there, which is surely nice and perhaps noble (depending on how you do it of course), that simply creates a new place that's analogous to Earth itself.

Kind of a hint of an insatiable cosmos-devouring demon that must conquer everywhere but can never enjoy the comfort of his own home. (not accusing you in particular of this, just painting a poetic picture :P)

I'm really excited about conquering hunger, poverty and curing severe mental illness, as a counterpoint.

Re: A sane but bull case on Clawdbot / OpenClaw

#416

Post by baby_souffle »

XorNot wrote: post #408
angiolillo wrote: post #372

Earlier quoted context omitted.

> Cataloguing your fridge requires taking pictures of everything you add and remove which seems... tedious. Just remember what you have? I agree that removing items and taking pictures takes more effort than it saves, but I would use a simpler solution if one existed because it turns out I cannot remember what we have. When my partner goes to the store I get periodic text messages from them asking how much X we have…

Fridge cataloging is actually a great use case for image recognition, the problem is fridges no accommodations to power accessories inside them. I have a couple of temperature sensors to alert Home Assistant if the fridge gets too warm. It would be easy and cheap to add some ESP32-camera modules to track contents...but there's no way to power them nicely (I simply don't know where I could pull USB power through).

Very very very flat cables don't mess with the gaskets on the door too much.

Re: A sane but bull case on Clawdbot / OpenClaw

#417

Post by polynomial »

louiereederson wrote: post #371
ribosometronome wrote: post #363

Earlier quoted context omitted.

>Why do you need a reminder to buy gloves when you are holding them? Am I missing this in the article? Do you mean the shoes he's holding? He explains it immediately. >when i visited REI this weekend to find running shoes for my partner, i took a picture of the shoe and sent it to clawdbot to remind myself to buy them later in a different color not available in store. the todo item clawdbot created was exceptionally…

Yes you are missing the picture where Brandon asks Linguini to add a reminder to buy a pair of Arc'Teryx gloves, which Brandon is holding in his hands.

I mean that's fine for people who can remember what they are holding, but not all of us can do that.

Re: A sane but bull case on Clawdbot / OpenClaw

#418

Post by polynomial »

kridsdale3 wrote: post #401
mananaysiempre wrote: post #356

Earlier quoted context omitted.

Claude said it couldn't do something, and the way around that was too tell it "yes you can". >kill dragon With what? Your bare hands? >yes Congratulations! You have just vanquished a dragon with your bare hands! (Unbelievable, isn't it?)

\> kill dragon -bash: kill: dragon: arguments must be process or job IDs \> sudo kill dragon -bash: Congratulations! You have just vanquished a dragon with your bare hands!

So, passwordless sudo, got it.

Re: A sane but bull case on Clawdbot / OpenClaw

#419

Post by heavyset_go »

louiereederson wrote: post #238

- Why do you need a reminder to buy gloves when you are holding them? - Why do you need price trackers for airbnb? It is not a superliquid market with daily price swings. - Cataloguing your fridge requires taking pictures of everything you add and remove which seems... tedious. Just remember what you have? - Can you not prepare for the next day by opening your calendar? - If you have reminders for everything (respond…

Imagine letting an LLM plan your day and it just decides to exclude things, shift stuff around and make it up wholesale.

If I wanted a buggy and flawed planning system that will certainly cause problems in the future, I'd start sticking post-it notes on a wall calendar and pray they don't fall off.

Re: A sane but bull case on Clawdbot / OpenClaw

#420

Post by kccqzy »

dewey wrote: post #266
louiereederson wrote: post #238

- Why do you need a reminder to buy gloves when you are holding them? - Why do you need price trackers for airbnb? It is not a superliquid market with daily price swings. - Cataloguing your fridge requires taking pictures of everything you add and remove which seems... tedious. Just remember what you have? - Can you not prepare for the next day by opening your calendar? - If you have reminders for everything (respond…

That is most of the "productivity" bubble, with AI or not. You are trying to fit everything into tightly defined processes, categories and methodologies to not have to actually sit down and do the work.

> if you're engineer-brained like me, you gravitate towards scripts and playbooks

Most people aren’t that engineer-brained like the author is. Me included; whatever the author does, it just doesn’t appeal to me.

Post reply on HN