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

531–540 of 1001 posts

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

#531

Post by wavemode »

jauntywundrkind wrote: post #448
wavemode wrote: post #223

Earlier quoted context omitted.

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.

The thought that occurs to me is, the action here that actually needs gating is maybe not the web browsing: it's accessing credentials. That should be relatively easy to gate off behind human approval! I'd also point out this a place where 2FA/MFA might be super helpful. Your phone or whatever is already going to alert you. There's a little bit of a challenge in being confident your bot isn't being tricked, in ascert…

You do need to gate the web browsing. 2FA and/or credential storage helps with passwords, but it doesn't help with other private information. If the claw is currently, or was recently, working with any files on your computer or any of your personal online accounts, then the contents of those files/webpages are in the model context. So a simple HTTP request to example.com/ presents the exact same risk.

You can take whatever risks you feel are acceptable for your personal usage - probably nobody cares enough to target an effective prompt-injection attack against you. But corporations? I would bet a large sum of money that within the next few years we will be hearing multiple stories about data breaches caused by this exact vulnerability, due to employees being lazy about limiting the claw's ability to browse the web.

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

#532

Post by roberttod »

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…

I created my own version with an inner llm, and outer orchestration layer for permissions. I don't think the OTP is needed here? The outer layer will ping me on signal when a tool call needs a permission, and an llm running in that outer layer looks at the trail up to that point to help me catch anything strange. I can then give permission once/ for a time limit/ forever on future tool calls.

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

#533

Post by phil21 »

thegrim33 wrote: post #394
stingraycharles wrote: post #24

Earlier quoted context omitted.

It’s as if ChatGPT is an autonomous agent that can do anything and keeps running constantly. Most AI tools require supervision, this is the opposite. To many people, the idea of having an AI always active in the background doing whatever they want them to do is interesting.

How do you need to supervise this "less" than an LLM that you can feed input to and get output back from? What does it mean that it's "running continuously"? Isn't it just waiting for input from different sources and responding to it? As the person you're replying to feels, I just don't understand. All the descriptions are just random cool sounding words/phrases strung together but none of it actually providing any c…

I’m sure there are other ways of doing what I’m doing, but openclaw was the first “package it up and have it make sense” project that captured my imagination enough to begin playing with AI beyond simple copy/paste stuff from chatGPT.

One example from last night: I have openclaw running on a mostly sandboxed NUC on my lab/IoT network at home.

While at dinner someone mentioned I should change my holiday light WLED pattern to St Patrick’s day vs Valentine’s Day.

I just told openclaw (via a chat channel) the wled controller hostname, and to propose some appropriately themes for the holiday, investigate the API, and go ahead and implement the chosen theme plus set it as the active sundown profile.

I came back home to my lights displaying a well chosen pattern I’d never have come up with outside hours of tinkering, and everything configured appropriately.

Went from a chore/task that would have taken me a couple hours of a weekend or evening to something that took 5 minutes or less.

All it was doing was calling out to Codex for this, but it acting as a gateway/mediator/relay for both the access channel part plus tooling/skills/access is the “killer app” part for me.

I also worked with it to come up with a promox VE API skill and it’s now repeatable able to spin up VMS with my normalized defaults including brand new cloud init images of Linux flavors I’ve never configured on that hypervisor before. A chore I hate doing so now I can iterate in my lab much faster. Also is very helpful spinning up dev environments of various software to mess with on those vms after creation.

I haven’t really had it be very useful as a typical “personal assistant” both due to lack of time investment and running against its (lack of) security model for giving it access to comms - but as a “junior sysadmin” it’s becoming quite capable.

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

#534

Post by soleveloper »

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…

Will that protect you from the agent changing the code to bypass those safety mechanisms, since the human is "too slow to respond" or in case of "agent decided emergency"?

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

#535

Post by krackers »

throw03172019 wrote: post #347

What are people using Claws for? It is interesting to see it everywhere but I haven’t had any good ideas for using them. Anyone to share their use case? Thanks!

As far as I can tell it's mostly use-cases like "externalized claude code", accessible on mobile. Maybe the "agentic harness" is slightly tweaked for longer running tasks, but if it's really better claude code will copy the tweaks anyway, so I don't really see what the hype and point is.

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

#536

Post by selridge »

ranger_danger wrote: post #454
selridge wrote: post #359

Earlier quoted context omitted.

You don’t understand the allure of having a computer actually do stuff for you instead of being a place where you receive email and get yelled at by a linter?

Perhaps people are just too jaded about the whole "I'll never have to work again" or "the computer can do all my work for me" miracle that has always been just around the corner for decades.

I do t see either of those as the premise.

This is about getting the computer to do the stuff we had been promised computing would make easier, stuff that was never capital-H Hard but just annoying. Most of the real claw skills are people connecting stuff that has always been connectable but it has been so fiddly as to make it a full time side project to maintain, or you need to opt into a narrow walled garden that someone can monetize to really get connectivity.

Now you can just get an LLM to learn apple’s special calendar format so you can connect it to a note-taking app in a way that only you might want. You don’t need to make it a second job to learn whatever glue needs to make that happen.

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

#537

Post by botusaurus »

andai wrote: post #335

We got store-brand Claw before GTA VI. For real though, it's not that hard to make your own! NanoClaw boasted 500 lines but the repo was 5000 so I was sad. So I took a stab at it. Turns out it takes 50 lines of code. All you need is a few lines of Telegram library code in your chosen language, and `claude -p prooompt`. With 2 lines more you can support Codex or your favorite infinite tokens thingy :) https://github.c…

you need to add cron to have a claw

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

#538

Post by ezst »

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…

Now we do computing like we play Sim City: sketching fuzzy plans and hoping those little creatures behave the way we thought they might. All the beauty and guarantees offered by a system obeying strict and predictable rules goes down the drain, because life's so boring, apparently.

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

#539

Post by mejutoco »

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…

Any website could in theory provide api access. But websites do not want this in general: remember google search api? Agents will run into similar restrictions for some cases as apis. It is not a technical problem imo, but an incentives one.

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

#540

Post by esafak »

anewhnaccount2 wrote: post #109
keiferski wrote: post #52

Earlier quoted context omitted.

The real-world cyberpunk dystopia won’t come with cool company names like Arasaka, Sense/Net, or Ono-Sendai. Instead we get childlike names with lots of vowels and alliteration.

Except Phillip K Dick calls the murder bots in Second Variety claws already so there's prior art right from the master of cyberpunk.

Better to be a claw than a skinjob!
Post reply on HN