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

NanoClaw moved from Apple Containers to Docker

twitter.com

Post reply on HN
Print view View original

111–120 of 146 posts

Re: NanoClaw moved from Apple Containers to Docker

#111

Post by mlsu »

signatoremo wrote: post #64
mpweiher wrote: post #48

Earlier quoted context omitted.

Dunno, my calendar reminds me "out of the blue", without me having to initiate a conversation, that it's time to leave for the gym, no "claw" or "ai" involved. I always have my backpack with me, so if I need milk I can pick it up on the way back. And I am pretty sure that I have to notice if I need milk myself. The tech sounds cool, but whenever I hear about actual applications, I don't see the point.

That's because you just lack of imagination. Imagine if you have a human personal assistant, what would you ask them to do? Examples: "Find me the cheapest ticket to Las Vegas for the first week of June. Buy one at anytime that you think is reasonable. Wait until no later than two months from now before buying. Get two tickets if my brother can also go". "Email me if anyone posts a Sega multi mega for sale. But only…

If I had a human personal assistant, I'd tell him to clean my gutters, sweep the driveway, clean the kitchen table...

I understand, if we imagine a world where everyone is constantly plugged into the computer all the time, and every bit of human activity is coordinated and surveilled by the computer at all times, this shit appears to be quite useful. Otherwise and even if, it's total schlock.

Like, "hey openclaw can you order me groceries" is great, but the only reason is that there's a wageslave on the other side of that transaction who has to drive to the grocery storef and pick the groceries out. Pretty soon that slave is going to be all of us and my god it makes me feel like an insane person that the boosters of this tech don't see that.

Re: NanoClaw moved from Apple Containers to Docker

#112

Post by mpweiher »

enraged_camel wrote: post #109
mpweiher wrote: post #105

Earlier quoted context omitted.

Thank you for illustrating my point perfectly: none of these scenarios you give as examples are things that resonate with me at all , and I wouldn't delegate them to a human personal assistant either.

I mean, yes, some people have real issues with delegating tasks to others. Those people probably wouldn't get much benefit from an... AI assistant. That doesn't "illustrate your point", it just states the obvious.

You are confusing "issues" with "lack of need" and "lack of benefit of proposed solution".

Again, I think the tech is cool, and I would actually really like to both better understand and try out the tech. But to try something out in earnest, I need some concrete use-case, and so far the use-cases I have seen range from "meh" to "get it away from me".

For agentic coding, I also needed some concrete use cases, and I found where it worked really well, where it struggles, and where it's just horrible.

Re: NanoClaw moved from Apple Containers to Docker

#113

Post by mpweiher »

signatoremo wrote: post #101
echoangle wrote: post #73

Earlier quoted context omitted.

> Imagine if you have a human personal assistant, what would you ask them to do? That’s kind of the confusing thing for me, I wouldn’t have a human personal assistant do anything for me as long as any money is on the line. I couldn’t teach them my preferences well enough to trust them to do it the way I want, instead of just doing it myself. Personal assistants only make sense to me if you’re so rich that money doesn…

> I wouldn’t have a human personal assistant do anything for me as long as any money is on the line. You don’t have to trust them with money. You can ask them to send you the info for you to do the final step. > Your trip booking thing for example is something I would never give to a human assistant. Maybe not you, but people already use personal travel agency for their booking need, see for example: https://www.redd…

Yes, there are probably people for whom this sort of thing can work.

For example, when I was at M$, management came to us extolling the virtues of Cortana and the then new "smart inbox". The manager was ecstatic. And for him, it maybe really was the neatest thing since sliced bread. And I know plenty of people with 10000+ unread in their INBOX. For them, it might be lifesaver.

But all the engineers in the room were "eek, get it away from me and make sure it never gets near my inbox". I personally maintain an INBOX-0 policy, not always perfectly, but it works for me. Unreads never last for more than a few minutes. So I have "situational awareness" of my e-mail, and when Apple also introduced smart inboxes, they broke that situational awareness while adding nothing whatsoever to my benefit. And people I communicate with also started losing e-mails, because they got sorted somewhere they weren't expecting.

So turn that shit off.

Re: NanoClaw moved from Apple Containers to Docker

#114

Post by lm28469 »

dmix wrote: post #84
lm28469 wrote: post #41

Earlier quoted context omitted.

There is no special sauce, it's mass hysteria driven by fake adoption metrics and people who don't know anything about computers who let "agents" run free on theirs. It's the equivalent of showing a magician cut a women in a box in half to a 5 years old kid... Put them in the same category as the neckbeards getting a hard on every 3 weeks for the past 2 years when they get to see the new version of ThE PeLiCaN On A B…

This is a classic early internet style snarky comment you used to find all over forums

> Some comments were wrong about one thing long ago hence every comments remotely similar about any other remotely similar thing will always be wrong

That's how this argument sounds... And it really isn't a strong argument

Re: NanoClaw moved from Apple Containers to Docker

#115

Post by lm28469 »

enraged_camel wrote: post #107
lm28469 wrote: post #41

Earlier quoted context omitted.

There is no special sauce, it's mass hysteria driven by fake adoption metrics and people who don't know anything about computers who let "agents" run free on theirs. It's the equivalent of showing a magician cut a women in a box in half to a 5 years old kid... Put them in the same category as the neckbeards getting a hard on every 3 weeks for the past 2 years when they get to see the new version of ThE PeLiCaN On A B…

Damn son, you sure sound salty!

Better salty than tricked by smoke and mirrors into thinking the singularity will happen in two release cycles and that chatgpt will cure cancer and poverty by 2028 lmao

Re: NanoClaw moved from Apple Containers to Docker

#116

Post by aitchnyu »

_pdp_ wrote: post #61

You don't need to use OpenClaw, NanoClaw or any of these new variants. You can literally use Codex, Claude Code, Gemini, OpenCode for the same thing. The only thing that it is missing from all of them is the communication channels because none of them come with native communication tools like OpenClaw. But this is not such a big deal. I made an open-source lightweight daemon in Go that fills that gap. All it does is…

Umm, is it out of the grey area of Whatsapp (and others') TOS?

Re: NanoClaw moved from Apple Containers to Docker

#117

Post by saberience »

crimsonnoodle58 wrote: post #91
mh2266 wrote: post #80

Earlier quoted context omitted.

I hear a lot about people doing this but it really seems like it is prompt injection as a service. eventually the things that can happen when you give the world write access to an unattended LLM that can access both your browser and password reset mechanism will happen. or someone will just make it email lewd pics to people’s bosses for the lols

That theory is being tested. So far no prompt injection has broken in: https://hackmyclaw.com/

Mostly because no one cares about trying to hack "hackmyclaw", there is zero value for any serious attacker to try. Why would they waste their time on a zero value target?

The only people who tried to hack "hackmyclaw" are casual attempts from HN readers when it was first posted.

Meanwhile, tons of actual OpenClaw users have been owned by malware which was downloaded as Skills.

Also, there have been plenty of actual examples of prompt injection working, including attacks on major companies. E.g. Superhuman was hacked recently via prompt injection.

Re: NanoClaw moved from Apple Containers to Docker

#118

Post by phanimahesh »

splatzone wrote: post #70
_pdp_ wrote: post #61

You don't need to use OpenClaw, NanoClaw or any of these new variants. You can literally use Codex, Claude Code, Gemini, OpenCode for the same thing. The only thing that it is missing from all of them is the communication channels because none of them come with native communication tools like OpenClaw. But this is not such a big deal. I made an open-source lightweight daemon in Go that fills that gap. All it does is…

What about heartbeats, cron etc? Seems like a major part of the 'claw' appeal is that it can work autonomously, monitor your email inbox for stuff and take action automatically...

Crontab entry to read a file and run a prompt?

Re: NanoClaw moved from Apple Containers to Docker

#119

Post by bookaway »

_pdp_ wrote: post #61

You don't need to use OpenClaw, NanoClaw or any of these new variants. You can literally use Codex, Claude Code, Gemini, OpenCode for the same thing. The only thing that it is missing from all of them is the communication channels because none of them come with native communication tools like OpenClaw. But this is not such a big deal. I made an open-source lightweight daemon in Go that fills that gap. All it does is…

It is truly odd in a way. You had posts here about Google managers or execs saying AI coded something solid in a few days what their own team were working on for months or years, or something along those lines. But people seem to ignore that creating a clone of your favorite "Claw" product seems like an ideal first project for the sea of mid or senior engineers that haven't dipped their toes into the vibe-coding ocean.

You have people talking about the tired topic of the lack of moat for AI businesses. But people should be calling out the moat that most tech businesses take for granted. Forget the moat that prevents other businesses, what about the moat that prevents your own users from creating your own product "from scratch"?

Re: NanoClaw moved from Apple Containers to Docker

#120

Post by mh2266 »

crimsonnoodle58 wrote: post #91
mh2266 wrote: post #80

Earlier quoted context omitted.

I hear a lot about people doing this but it really seems like it is prompt injection as a service. eventually the things that can happen when you give the world write access to an unattended LLM that can access both your browser and password reset mechanism will happen. or someone will just make it email lewd pics to people’s bosses for the lols

That theory is being tested. So far no prompt injection has broken in: https://hackmyclaw.com/

https://x.com/benhylak/status/2025873646724800835

turns out it doesn’t even need to be an attacker…

Post reply on HN