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

901–910 of 1001 posts

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

#901

Post by selridge »

tovej wrote: post #886
selridge wrote: post #858

Earlier quoted context omitted.

I’ll give you a real concrete example. I had to build an app on the Mac, which needed to be signed. I did not want to learn Apple signing procedures in order to do this. It turns out I did not have to, because I got the robot to learn it. So then I was able to finish doing what it was I intended to do without having to spend an afternoon or a day misunderstanding the Apple signing procedures. Could I have learned the…

A full adder is literally one of the easier theoretical computer science concepts, and a sine approximation is a simple Maclaurin series. And yes, if you can't do a simple series expansion, you are not an engineer. You may be a developer, but not an engineer. These are both first or second year bachelors topics. Just because you're unable to work through simple math problems doesn't mean any semi-competent computer p…

Was it a good thing for anyone writing software which included those things to need to not only work out how they are on a blackboard but how they are on the real machine in question? And how they are on the next machine over?

Do you yearn to return to that world? I suspect most people don't. It's not just knowing your own machine, but any machine the code could run on. It's also not just reaching for some 2nd year bachelor topics when the matter at hand is much more complicated. Where does your sine approximation fail? How do you know? Can you prove that? Does the compiler or the hardware decide to do things behind your back which vitiate any of those claims?

Knowing the answer to that all every time you need a sine is not something 99.99% of engineers need to worry about. IT USED TO BE. But now it's not. No one is going back to that.

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

#902

Post by catlifeonmars »

Gareth321 wrote: post #822
corndoge wrote: post #746

I still don't understand what openclaw is or does and i've read the docs multiple times over. "Any OS gateway for AI agents across WhatsApp, Telegram, Discord, iMessage, and more. Send a message, get an agent response from your pocket. Plugins add Mattermost and more." "What is OpenClaw? OpenClaw is a self-hosted gateway that connects your favorite chat apps — WhatsApp, Telegram, Discord, iMessage, and more — to AI c…

It was surprisingly difficult for me to understand the use case as well. Here is my best attempt at an elevator pitch: At present your memories are proprietary data in whichever LLM you use. ChatGPT keeps all your conversations and output and data forever. What if you don't like GPT 5.2? What if you want to use other models as well? Or use the best model for the job? OpenClaw gives you that ability. Your memories and…

> We already have examples of these agents creating an AI religion, an AI social network (which debated how to keep humans out using a human captcha), attempting to legally separate from their creators

Didn’t these turn out to be fake and/or humans cosplaying as bots?

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

#903

Post by ErneX »

lwhi wrote: post #662
ErneX wrote: post #193

Earlier quoted context omitted.

They recommend a Mac Mini because it’s the cheapest device that can access your Apple reminders and iMessage. If you are into that ecosystem obviously. If you don’t need any of that then any device or small VPS instance will suffice.

It's because of the Mac Mini's unified memory architecture; which is ideal for inference.

The amount of ram available on a Mac Mini is not good enough for a decent open model for OpenClaw, everybody is using remote AI services on those.

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

#904

Post by deejaaymac »

paulryanrogers wrote: post #899
PantaloonFlames wrote: post #875

Earlier quoted context omitted.

Cmon man. “Consumers” in aggregate. Not “every consumer”. But you knew that.

Many consumers want things that are arguably harmful for everyone involved. Users asking Grok to generate a large amount of CSAM from kid pics on Twitter is but one example.

Just to clarify; you're comparing nuclear weapons to lines of code that generate text/images?

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

#905

Post by Loughla »

michaelmrose wrote: post #872
simondotau wrote: post #612

Earlier quoted context omitted.

Being rude isn't helpful. It's not their fault, it's the unavoidable reality of treating complex social signalling as one-dimensional. At minimum Hacker News would need to separate approval/disapproval signals from assessments of whether a comment is constructive. That’s not a simple change given the obvious abuse vectors. It would require reliably distinguishing good-faith participants from bad actors. It can be don…

I really like the idea of multiple vectors although nobody seems apt to pick up the idea other than Slashdot.

The reason I left there was the down vote brigade that really killed most genuine criticism that disagrees with the sites pre formed opinions on certain topics. So I'm not sure it's a solved problem. Unless it's gotten better since 2011?

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

#906

Post by billmalarky »

jbxntuehineoh wrote: post #674
billmalarky wrote: post #458

Earlier quoted context omitted.

Bastion hosts. You don't give it your "prod email", you give it a secondary email you created specifically for it. You don't give it your "prod Paypal", you create a secondary paypal (perhaps a paypal account registered using the same email as the secondary email you gave it). You don't give it your "prod bank checking account", you spin up a new checking with Discover.com (or any other online back that takes Now the…

isn't the value proposition "it can read your email and then automatically do things"? if it can't read your email and then can't actually automatically do things... what's the point?

Yes -- definitely that's the value prop. But it's not binary all or nothing.

AI automation is about trust (honestly, same as human delegation).

You give it access to a little bit of data, just enough to do a basic useful thing or two, then you give it a bit of responsibility.

Then as you build confidence and trust, you give it a little more access, and allow it to take on a little more responsibility. Naturally, if it blows up in your face, you dial back access and responsibility quick.

As an analogy, folks drive their cars on the highway at 65-85+ MPH. Fatality rate goes up somewhat exponentially with speed and anything 60+ is considerably more deadly than ~30mph.

We're all so confident that a wheel won't randomly fall off because we've built so much trust with the quality of modern automobiles. But it does happen (I had a friend in high-school who's wheel popped off on a 45 mph road -- naturally he was going 50-55 IIRC).

In the early 1900s people would have thought you had a death wish to drive this fast. 25-30mph was normal then -- the automobiles at the time just weren't developed enough to be trusted at higher speeds.

My previous comment was about the fact that it is possible to build this sandboxing/bastion layer with live web accounts that allows for fine grained control over how much data you want to expose to the ai.

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

#907

Post by athrowaway3z »

corndoge wrote: post #746

I still don't understand what openclaw is or does and i've read the docs multiple times over. "Any OS gateway for AI agents across WhatsApp, Telegram, Discord, iMessage, and more. Send a message, get an agent response from your pocket. Plugins add Mattermost and more." "What is OpenClaw? OpenClaw is a self-hosted gateway that connects your favorite chat apps — WhatsApp, Telegram, Discord, iMessage, and more — to AI c…

Easy set up + WhatsApp messages + wakes up regularly to make it feel more alive + larger memory (local fs) => non-dev fascination

I think the issue you have is one of perspective.

Reminds me of the Dropbox launch on HN where the top comment was something like:

> Yes but why not just rsync?

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

#908

Post by ekjhgkejhgk »

athrowaway3z wrote: post #907
corndoge wrote: post #746

I still don't understand what openclaw is or does and i've read the docs multiple times over. "Any OS gateway for AI agents across WhatsApp, Telegram, Discord, iMessage, and more. Send a message, get an agent response from your pocket. Plugins add Mattermost and more." "What is OpenClaw? OpenClaw is a self-hosted gateway that connects your favorite chat apps — WhatsApp, Telegram, Discord, iMessage, and more — to AI c…

Easy set up + WhatsApp messages + wakes up regularly to make it feel more alive + larger memory (local fs) => non-dev fascination I think the issue you have is one of perspective. Reminds me of the Dropbox launch on HN where the top comment was something like: > Yes but why not just rsync?

> Reminds me of the Dropbox launch on HN where the top comment was something like:

> > Yes but why not just rsync?

Commenting on this comment is so out of date. Dropbox is an anti-user pile of shit, and rsync is way better.

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

#909

Post by jb1991 »

UncleMeat wrote: post #613
jb1991 wrote: post #525

Earlier quoted context omitted.

You can debate the meaning of the word pioneer but think of it this way: OpenAI created this new AI boom, and Andrej is a co-founder of the company that did that.

Would you say that Musk is one of the most significant AI pioneers in history? I don't personally believe that founding the organization is more meaningful than doing the actual work.

The difference is that Andrej is an actual AI engineer who remained involved in the company. Musk was just an early co-founder who eventually left and had no involvement on the breakthroughs of the company.

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

#910

Post by irishcoffee »

javier123454321 wrote: post #878
aleph_minus_one wrote: post #874

Earlier quoted context omitted.

> I don't understand why people use Gmail. Just get a VPS and set up a SMTP server. This would indeed be a good idea. The problem is that other email providers will often reject your emails (e.g. because they consider your emails to be spam or simply don't trust your server), so this idea is not easy to get to work. So the next best solution is to use an email provider that is somewhat established (avoiding the menti…

I'm sorry you might have missed the part where I was being sarcastic. Setting up your own SMTP server is actually literally a bad idea for the most part. Unless you want to debug your own mail server. Which, I promise you, 99% of users using gmail do not, and should not.

Handing your digital life to a claw bot that was vibe coded however, is a good idea?
Post reply on HN