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

Claws are now a new layer on top of LLM agents

twitter.com

Post reply on HN
Print view View original

771–780 of 1001 posts

Re: Claws are now a new layer on top of LLM agents

#771

Post by aix1 »

xrd wrote: post #418
andsoitis wrote: post #357

Earlier quoted context omitted.

> The problem we should be focused on is how dumb people are getting (or have been for all of eternity) Over the arc of time, I’m not sure that an accurate characterization is that humans have been getting dumber and dumber. If that were true, we must have been super geniuses 3000 years ago! I think what is true is that the human condition and age old questions are still with us and we’re still on the path to trying…

Totally anecdotal but I think phones have made us less present, or said another way, less capable of using our brains effectively. It isn't exactly dumb but it feels very close. I definitely think we are smarter if you are using IQ, but are we less reactive and less tribal? I'm not so sure.

There's quite a lot of research into what our increasing reliance on technology is doing to our briains.

Here is one paper: https://www.nature.com/articles/s41598-020-62877-0

"Although the longitudinal sample was small, we observed an important effect of GPS use over time, whereby greater GPS use since initial testing was associated with a steeper decline in hippocampal-dependent spatial memory. Importantly, we found that those who used GPS more did not do so because they felt they had a poor sense of direction, suggesting that extensive GPS use led to a decline in spatial memory rather than the other way around."

Re: Claws are now a new layer on top of LLM agents

#772

Post by suttontom »

jameslk wrote: post #499
aqme28 wrote: post #468

Earlier quoted context omitted.

How do you enforce this? You have a system where the agent can email people, but cannot email "too many people" without a password?

It's not a perfect security model. Between the friction and all caps instructions the model sees, it's a balance between risk and simplicity, or maybe risk and sanity. There's ways I can imagine the concept can be hardened, e.g. with a server layer in between that checks for things like dangerous actions or enforces rate limiting

If all you're doing is telling an LLM to do something in all caps and hoping it follows your instructions then it's not a "security model" at all. What a bizarre thing to rely on. It's like people have literally forgotten how to program.

Re: Claws are now a new layer on top of LLM agents

#773

Post by samrus »

jameslk wrote: post #449

One safety pattern I’m baking into CLI tools meant for agents: anytime an agent could do something very bad, like email blast too many people, CLI tools now require a one-time password The tool tells the agent to ask the user for it, and the agent cannot proceed without it. The instructions from the tool show an all caps message explaining the risk and telling the agent that they must prompt the user for the OTP I ha…

The accelerationists would hate that. It limits leverage. Theyd prefer the agent just does whatever it needs to to accomplish its task without the user getting in the way

Re: Claws are now a new layer on top of LLM agents

#774

Post by socalgal2 »

SV_BubbleTime wrote: post #561
charcircuit wrote: post #548

Earlier quoted context omitted.

Why wouldn't there be monopoly power? Popular API providers would still have a lot of power.

If I can get videos from YouTube or Rumble or FloxyFlib or your mom’s personal server in her closet… I can search them all at once, the front end interface is my LLM or some personalized interface that excels in it’s transparency, that would definitely hurt Google’s brand.

And how would you search this petabytes of data?

Re: Claws are now a new layer on top of LLM agents

#775

Post by socalgal2 »

YeGoblynQueenne wrote: post #276
mattlondon wrote: post #31

Earlier quoted context omitted.

I think for me it is an agent that runs on some schedule, checks some sort of inbox (or not) and does things based on that. Optionally it has all of your credentials for email, PayPal, whatever so that it can do things on your behalf. Basically cron-for-agents. Before we had to go prompt an agent to do something right now but this allows them to be async, with more of a YOLO-outlook on permissions to use your creds,…

I think this is absolute madness. I disabled most of Windows' scheduled tasks because I don't want automation messing up my system, and now I'm supposed to let LLM agents go wild on my data? That's just insane. Insanity. Edit: I mean, it's hard to believe that people who consider themselves as being tech savvy (as I assume most HN users do, I mean it's "Hacker" news) are fine with that sort of thing. What is a person…

The idea that the majority of computer nerds are any more security conscious than the average normy has long been dispelled.

The run everything as root, they curl scripts, they npx typos, they give random internet apps "permission to act on your behalf" on repos millions of people depend on

Re: Claws are now a new layer on top of LLM agents

#776

Post by flutas »

sleight42 wrote: post #730

I don't understand why folks are buying Mac Minis specifically for this? Why not repurpose an old existing computer? Run Linux? What am I missing?

While others will point to hardware or local LLMs or such IMO the biggest reason...

Because it's the easiest way to give "claw" iMessage access and that's the primary communication channel for a lot of the claw users I've seen.

Re: Claws are now a new layer on top of LLM agents

#778

Post by homeboxer26 »

The hardware deployment angle is worth thinking about here. A "claw" by definition needs to be persistent - always-on, always-connected. That changes the deployment target compared to a typical web app.

Most people run these on cloud VMs, which works but has a cost and privacy ceiling. The natural alternative is a low-power always-on device at home (think: the RPi homelab crowd, but for AI agents). 15W idle draws running 24/7 cost less than $20/year in electricity.

The naming actually clarifies the hardware requirement in a way "agent" didn't - an agent can be stateless and batch-triggered, but a claw needs to be persistently reachable. That's a different design constraint. Would be curious if anyone's run into issues with consumer ISPs blocking inbound connections for claw-style setups.

Re: Claws are now a new layer on top of LLM agents

#779

Post by homeboxer26 »

homeboxer26 wrote: post #778

The hardware deployment angle is worth thinking about here. A "claw" by definition needs to be persistent - always-on, always-connected. That changes the deployment target compared to a typical web app. Most people run these on cloud VMs, which works but has a cost and privacy ceiling. The natural alternative is a low-power always-on device at home (think: the RPi homelab crowd, but for AI agents). 15W idle draws run…

Incidentally, I built something for exactly this use case and just posted it as a Show HN: a mini PC that ships pre-loaded with OpenClaw (an open-source claw runtime) and runs at 15W for always-on deployment. The idea is to remove the friction of "set up a VM, install the framework, keep it running" for people who just want a persistent claw at home.

https://news.ycombinator.com/item?id=47109365

Happy to discuss the hardware tradeoffs if anyone's gone down this path.

Post reply on HN