Claws are now a new layer on top of LLM agents • Hacker News Board

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

#241

Post by wavemode » Sat, Feb 21, 2026, 2:23 PM UTC

igravious wrote: post #188

snovv_crash wrote: post #48

Earlier quoted context omitted.

Cron would be for a polling model. You can also have an interrupts/events model that triggers it on incoming information (eg. new email, WhatsApp, incoming bank payments etc). I still don't see a way this wouldn't end up with my bank balance being sent to somewhere I didn't want.

> I still don't see a way 1) don't give it access to your bank 2) if you do give it access don't give it direct access (have direct access blocked off and indirect access 2FA to something physical you control and the bot does not have access to) --- agreed or not? --- think of it like this -- if you gave a human power to drain you bank balance but put in no provision to stop them doing just that would that personal a…

The difference there would be that they would be guilty of theft, and you would likely have proof that they committed this crime and know their personal identity, so they would become a fugitive.

By contrast with a claw, it's really you who performed the action and authorized it. The fact that it happened via claw is not particularly different from it happening via phone or via web browser. It's still you doing it. And so it's not really the bank's problem that you bought an expensive diamond necklace and had it shipped to Russia, and now regret doing so.

Imagine the alternative, where anyone who pays for something with a claw can demand their money back by claiming that their claw was tricked. No, sir, you were tricked.

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

#242

Post by ghostclaw-cso » Sat, Feb 21, 2026, 2:23 PM UTC

[flagged]

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

#243

Post by esafak » Sat, Feb 21, 2026, 2:24 PM UTC

wavemode wrote: post #223

bpicolo wrote: post #176

Earlier quoted context omitted.

Don't give it write permissions? You could easily make human approval workflows for this stuff, where humans need to take any interesting action at the recommendation of the bot.

The mere act of browsing the web is "write permissions". If I visit example.com/ , I've now written my password into the web server logs of that site. So the only remaining question is whether I can be tricked/coerced into doing so. I do tend to think this risk is somewhat mitigated if you have a whitelist of allowed domains that the claw can make HTTP requests to. But I haven't seen many people doing this.

Most web sites don't let you create service accounts; they're built for humans.

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

#244

Post by strix_varius » Sat, Feb 21, 2026, 2:24 PM UTC

alansaber wrote: post #220

krtagf wrote: post #165

[flagged]

We construct a circus around everything, that's the nature of human attention :), why are people so surprised by pop compsci when pop physics has been around forever.

Pop physics influences less of our day-to-day lives though.

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

#245

Post by embedding-shape » Sat, Feb 21, 2026, 2:26 PM UTC

trcf23 wrote: post #235

Has anyone find a useful way to to something with Claws without massive security risk? As a n8n user, i still don't understand the business value it adds beyond being exciting... Any resources or blog post to share on that?

> Has anyone find a useful way to to something with Claws without massive security risk?

Not really, no. I guess the amount of integrations is what people are raving about or something?

I think one of the first thing I did when I got access to codex, was to write a harness that lets me fire off jobs via a webui on a remote access, and made it possible for codex to edit and restart it's own process, and send notifications via Telegram. Was a fun experiment, still use it from time to time, but it's not a working environment, just a fun prototype.

I gave openclaw a try some days ago, and besides that the setup wrote config files that had syntax errors, it couldn't run in a local container and the terminology is really confusing ("lan-only mode" really means "bind to all found interfaces" for some stupid reason), the only "benefit" I could see would be the big amount of integrations it comes with by default.

But it seems like such a vibeslopped approach, as there is a errors and nonsense all over the UI and implementation, that I don't think it'll manageable even in the short-term, it seems to already have fallen over it's own spaghetti architecture. I'm kind of shocked OpenAI hired the person behind it, but they also probably see something we from the outside cannot even see, as they surely weren't hired because of how openclaw was implemented.

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

#246

Post by embedding-shape » Sat, Feb 21, 2026, 2:29 PM UTC

leprechaun1066 wrote: post #215

logicprog wrote: post #189

Earlier quoted context omitted.

This doesn't seem to be promoting every new monstrosity? "m definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all. Already seeing reports of exposed instances, RCE vulnerabilities, supply chain poisoning, malicious or compromised skills in the registry, it feels like a complete wild we…

> just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

> Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

I mean we're on layer ~10 or something already right? What's the harm with one or two more layers? It's not the typical JavaScript developer understands all layers down to what the hardware is doing anyways.

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

#247

Post by jryan49 » Sat, Feb 21, 2026, 2:30 PM UTC

claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

I mean we know at this point it's not super intelligent AGI yet, so I guess we don't care.

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

#248

Post by andsoitis » Sat, Feb 21, 2026, 2:33 PM UTC

embedding-shape wrote: post #246

leprechaun1066 wrote: post #215

Earlier quoted context omitted.

> just like LLM agents were a new layer on top of LLMs, Claws are now a new layer on top of LLM agents, taking the orchestration, scheduling, context, tool calls and a kind of persistence to a next level. Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well...

> Layers of "I have no idea what the machine is doing" on top of other layers of "I have no idea what the machine is doing". This will end well... I mean we're on layer ~10 or something already right? What's the harm with one or two more layers? It's not the typical JavaScript developer understands all layers down to what the hardware is doing anyways.

I will assume you know that comparison is apples and oranges. If you don’t, I’d be happy to explain.

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

#249

Post by throwaway13337 » Sat, Feb 21, 2026, 2:34 PM UTC

The real big deal about 'claws' in that they're agents oriented around the user.

The kind of AI everyone hates is the stuff that is built into products. This is AI representing the company. It's a foreign invader in your space.

Claws are owned by you and are custom to you. You even name them.

It's the difference between R2D2 and a robot clone trying to sell you shit.

(I'm aware that the llms themselves aren't local but they operate locally and are branded/customized/controlled by the user)

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

#250

Post by wiseowise » Sat, Feb 21, 2026, 2:35 PM UTC

claytonaalves wrote: post #219

I'm impressed with how we moved from "AI is dangerous", "Skynet", "don't give AI internet access or we are doomed", "don't let AI escape" to "Hey AI, here is internet, do whatever you want".

> “we”

Bunch of Twitter lunatics and schizos are not “we”.