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

511–520 of 1001 posts

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

#511

Post by fsloth »

daxfohl wrote: post #460

I wonder how the internet would have been different if claws had existed beforehand. I keep thinking something simpler like Gopher (an early 90's web protocol) might have been sufficient / optimal, with little need to evolve into HTML or REST since the agents might be better able to navigate step-by-step menus and questionnaires, rather than RPCs meant to support GUIs and apps, especially for LLMs with smaller contex…

> if claws had existed beforehand.

That's literally not possible would be my take. But of course just intuition.

The dataset used to train LLM:s was scraped from an internet. The data was there mainly due to the user expansion due to www, and the telco infra laid during and after dot-com boom that enabled said users to access web in the first place.

The data labeling which underpins the actual training, done by masses of labour, on websites, could not have been scaled as massively and cheaply without www scaled globally with affordable telecoms infra.

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

#512

Post by sowbug »

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…

Another pattern would mirror BigCorp process: you need VP approval for the privileged operation. If the agent can email or chat with the human (or even a strict, narrow-purpose agent(1) whose job it is to be the approver), then the approver can reply with an answer.

This is basically the same as your pattern, except the trust is in the channel between the agent and the approver, rather than in knowledge of the password. But it's a little more usable if the approver is a human who's out running an errand in the real world.

1. Cf. Driver by qntm.

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

#513

Post by dw_arthur »

nsonha wrote: post #290

I find it dubious that a technical person claims to "just bought a new Mac mini to properly tinker with claws over the weekend". Like can they not just play with it on an old laptop lying around? A virtual machine? Or why did they not buy a Pi instead? Openclaw works with linux so not sure how this whole Mac mini cliche even started, obviously an overkill for something that only relays api calls.

As a long time computer hobbyist who grew up in MSDOS and now resides in Linux I'm starting to wonder if I am not more connected to computing than a lot of people employed in the field.

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

#514

Post by hamburglar »

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 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 as human intervention or whitelists. And this isolated process could be LLM-driven also (so it could make more sophisticated decisions about “is this ok”) but never exposed to untrusted input.

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

#515

Post by toraway »

yks wrote: post #297
bravura wrote: post #102

Earlier quoted context omitted.

There are a few qualitative product experiences that make claw agents unique. One is that it relentlessly strives thoroughly to complete tasks without asking you to micromanage it. The second is that it has personality. The third is that it's artfully constructed so that it feels like it has infinite context. The above may sound purely circumstantial and frivolous. But together it's the first agent that many people w…

> it's the first agent that many people who usually avoid AI simply LOVE. Not arguing with your other points, but I can't imagine "people who usually avoid AI" going through the motions to host OpenClaw.

It's classic hype/FOMO posturing.

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

#516

Post by holoduke »

ZeroGravitas wrote: post #26

So what is a "claw" exactly? An ai that you let loose on your email etc? And we run it in a container and use a local llm for "safety" but it has access to all our data and the web?

I am creating a claw that is basically a loop that runs every x minutes. It uses the Claude cli tool. And it builds a memory based on some kind of simple node system. With active memories and fading old memories. I also added functionality to add integrations like whatsapp, agenda. Slack and gmail. so every "loop" the ai reads in information and updates it's memory. There is also a directive that can decide to create tasks or directly message me or others. It's a bit of playing around. Very dangerous, but fun to play with. The application even has self improvement system. I creates a few pull requests every day it thinks is needed to make it better. Hugely fun to see it evolving. https://github.com/holoduke/myagent

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

#517

Post by sowbug »

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 I were the CEO of a place like Plaid, I'd be working night and day expanding my offerings to include a safe, policy-driven API layer between the client and financial services.

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

#518

Post by baq »

mystifyingpoi wrote: post #471
notepad0x90 wrote: post #455

Earlier quoted context omitted.

How about "Open Assistants"? "OpenAss" for short?

I like that, this name tells you all about the security implications. Like, your user data could be penetrated.

I like ‘claw’ because the s in it stands for security

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

#519

Post by alecco »

rane wrote: post #490
alecco wrote: post #430

> Bought a new Mac mini to properly tinker with claws over the weekend. Disappointing. There is a Rust-based assistant that can run comfortably in a Raspberry PI (or some very old computer you are not using) https://zeroclawlabs.ai/ https://github.com/zeroclaw-labs/zeroclaw (Built by Harvard and MIT students, looks like) EDIT: sorry top Google result led to a fake ZeroClaw!

This zeroclaw.org has to be some kind of malware. This is the official repo https://github.com/zeroclaw-labs/zeroclaw and its website: https://zeroclawlabs.ai/

Oof! Thanks for the catch. I fixed the links. I swear it's what I get as top Google results for both "zeroclaw" and "zeroclaw github".

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

#520

Post by alecco »

mikert89 wrote: post #433
alecco wrote: post #430

> Bought a new Mac mini to properly tinker with claws over the weekend. Disappointing. There is a Rust-based assistant that can run comfortably in a Raspberry PI (or some very old computer you are not using) https://zeroclawlabs.ai/ https://github.com/zeroclaw-labs/zeroclaw (Built by Harvard and MIT students, looks like) EDIT: sorry top Google result led to a fake ZeroClaw!

dude nobody cares about school prestige, the whole value in openclaw was that its an innovative idea, not that its written in Rust

From their GitHub repo: "Runs on $10 hardware with <5MB RAM: That's 99% less memory than OpenClaw and 98% cheaper than a Mac mini!"
Post reply on HN