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

981–990 of 1001 posts

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

#981

Post by whywhywhywhy »

zer00eyz wrote: post #303
deepsquirrelnet wrote: post #277

Earlier quoted context omitted.

The DoDs recent beef with Anthropic over their right to restrict how Claude can be used is revealing. > Though Anthropic has maintained that it does not and will not allow its AI systems to be directly used in lethal autonomous weapons or for domestic surveillance Autonomous AI weapons is one of the things the DoD appears to be pursuing. So bring back the Skynet people, because that’s where we apparently are. 1. http…

> Autonomous AI weapons In theory, you can do this today, in your garage. Buy a quad as a kit. (cheap) Figure out how to arm it (the trivial part). Grab yolo, tuned for people detection. Grab any of the off the shelf facial recognition libraries. You can mostly run this on phone hardware, and if you're stripping out the radios then possibly for days. The shim you have to write: software to fly the drone into the pers…

Judging by the ecohazard of fiber optics Ukraine has become I think it’s safe to say it can’t be this easy

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

#982

Post by lwhi »

ErneX wrote: post #953
lwhi wrote: post #934

Earlier quoted context omitted.

You can get up 64GB of memory. It's very difficult to get this much memory on a graphics card.

I know, but which open model that fits in there is useful enough for OpenClaw? I don’t think there is one. If you look at the videos and blog posts where they recommend getting a Mac Mini for this are recommending the base model (which comes with just 16GB), precisely because it’s the cheapest Mac that can read your reminders, use iMessage etc. that’s what those using OpenClaw want from the Mini, not its inference ca…

I disagree.

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

#983

Post by davedx »

bean469 wrote: post #938
davedx wrote: post #838

Earlier quoted context omitted.

I spent a few days running openclaw on a VPS, and it was painful and frustrating: - no graphics subsystem makes things harder - VPS IP subnets are often blocked by default by numerous websites and WAFs - can't easily see what it's doing Running it on its own PC is definitely the golden path for the way it's architected.

> Running it on its own PC is definitely the golden path for the way it's architected. Not really familiar with the architecture, but would it be possible to run it on a not so powerful laptop in a "client" mode, where it would query a LLM that is running on a more beefy desktop?

Yeah, one of the suggestions I encountered along the way was "run the Claw on the VPS but then have it tunnel to my laptop to run browser sessions". I think there are a myriad of ways to set this up.

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

#984

Post by yencabulator »

hamburglar wrote: post #514
YeGoblynQueenne wrote: post #276

Earlier quoted context omitted.

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 computer nerds understand how to isolate this stuff to mitigate the risk. I’m not in on openclaw just yet but I do know it’s got isolation options to run in a vm. I’m curious to see how they handle controls on “write” operations to everyday life. I could see something like having a very isolated process that can, for example, send email, which the claw can invoke, but the isolated process has sanity controls such…

> computer nerds understand

No, literally no one understands how to solve this. The only option that actually works is to isolate it to a degree that removes the "clawness" from it, and that's the opposite of what people are doing with these things.

Specifically, you cannot guard an LLM with another LLM.

The only thing I've seen with any realism to it is the variables, capabilities and taint tracking in CaMeL, but again that limits what the system can do and requires elaborate configuration. And you can't trust a tainted LLM to configure itself.

https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

https://simonwillison.net/2025/Jun/13/prompt-injection-desig...

https://simonwillison.net/2025/Apr/11/camel/

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

#985

Post by yencabulator »

squidbeak wrote: post #424
YeGoblynQueenne wrote: post #276

Earlier quoted context omitted.

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…

> and now I'm supposed to let LLM agents go wild on my data? Who is forcing you to do that? The people you are amazed by know their own minds and understand the risks.

That's the thing with rampant enthusiasm, nobody has to be forced into it, they'll do dumb things out of their own initiative.

> understand the risks

Here's the director of Safety and alignment at Meta Superintelligence deleting her emails and panicking: https://xcancel.com/summeryue0/status/2025774069124399363

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

#986

Post by yencabulator »

zmmmmm wrote: post #528

It seems like the people using these are writing off the risks - either they think it's so unlikely to happen it doesn't matter or they assume they won't be held responsible for the damage / harm / loss. So I'm curious how it will go down once serious harm does occur. Like someone loses their house, or their entire life savings or have their identity completely stolen. And these may be the better scenarios, because t…

For extra schadenfreude, here's apparently the Meta director of "Safety and alignment at Meta Superintelligence" accidentally deleting emails with a claw. That tells you that very few people stop to think, even of the people paid a lot of money to do exactly that:

https://xcancel.com/summeryue0/status/2025774069124399363

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

#988

Post by krzyk »

javier123454321 wrote: post #864
krzyk wrote: post #829

Earlier quoted context omitted.

I had exact same issue with it. I don't get it. Integration of LLM with chating services is simple, how does it change anything?

It's simple if you've done that work before, or if you consider yourself little more technical, this is a turnkey solution that does that. I don't understand why people use Gmail. Just get a VPS and set up a SMTP server. Why would anyone use Squarespace you can code an HTML page in a day and upload it to a static site hosting service.

Email is a bad example, it is quite closed system compared to, well everything else.

One cannot just telnet and send email (that will get delivered) these days, unfortunately.

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

#989

Post by hamburglar »

yencabulator wrote: post #984
hamburglar wrote: post #514

Earlier quoted context omitted.

The computer nerds understand how to isolate this stuff to mitigate the risk. I’m not in on openclaw just yet but I do know it’s got isolation options to run in a vm. I’m curious to see how they handle controls on “write” operations to everyday life. I could see something like having a very isolated process that can, for example, send email, which the claw can invoke, but the isolated process has sanity controls such…

> computer nerds understand No, literally no one understands how to solve this. The only option that actually works is to isolate it to a degree that removes the "clawness" from it, and that's the opposite of what people are doing with these things. Specifically, you cannot guard an LLM with another LLM. The only thing I've seen with any realism to it is the variables, capabilities and taint tracking in CaMeL, but ag…

If the “clawness” means you only use the llm to control itself, then yes, that’s impossible. But you can easily shim such a process so that the interfaces it uses to “claw out” to the real world are shims that have safeties such as human control. Openclaw does not do this, and is thus a scary shit show, but you can play with it in isolation safely, and I think a standard pattern for good control will emerge.

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

#990

Post by yencabulator »

hamburglar wrote: post #989
yencabulator wrote: post #984

Earlier quoted context omitted.

> computer nerds understand No, literally no one understands how to solve this. The only option that actually works is to isolate it to a degree that removes the "clawness" from it, and that's the opposite of what people are doing with these things. Specifically, you cannot guard an LLM with another LLM. The only thing I've seen with any realism to it is the variables, capabilities and taint tracking in CaMeL, but ag…

If the “clawness” means you only use the llm to control itself, then yes, that’s impossible. But you can easily shim such a process so that the interfaces it uses to “claw out” to the real world are shims that have safeties such as human control. Openclaw does not do this, and is thus a scary shit show, but you can play with it in isolation safely, and I think a standard pattern for good control will emerge.

> easily

Yeah that's an active research topic for teams of PhDs, including some of Google's brightest. And the current approach even with added barriers may just be fundamentally untrustable. Read the links from my earlier comment for background.

Post reply on HN