Live data from Hacker News

Claws are now a new layer on top of LLM agents

twitter.com

721–730 of 1001 posts

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

#721
post #649

Security-wise, having a Claw doesn’t seem so different from having a traditional (human) assistant or working with a consultant. You wouldn’t give them access to your personal email or bank account. You’d set them up with their own email and a limited credit card.

>You wouldn’t give them access to your personal email or bank account. I thought it was vaguely common for secretaries (or staffers) to run the email/social media accounts of politicians and executives? Also you might not give access your secretary access to your bank account, but you'd give it to your financial adviser or accountant.

> I thought it was vaguely common for secretaries (or staffers) to run the email/social media accounts of politicians and executives?

Yes, that's correct. One of the many functions of an executive assistant for a senior executive is to manage the email inbox and the calendar. But even there, there are rules, even if they aren't technically enforced by Google Workspace or MS Exchange. Each principal has a slightly different set of rules with their EAs, and you could imagine similar differentiation with how people customize their own AI agents to get the best balance of keeping your inbox clean vs. not causing your email to turn into a weapon against you.

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

#722

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?

Setup automatic forwards. If I was to do this, I’d forward all the emails from my kids activities to its email.

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

#724

Earlier quoted context omitted.

In a VM or a separate host with access to specific credentials in a very limited purpose. In any case, the data that will be provided to the agent must be considered compromised and/or having been leaked. My 2 cents.

Maybe I'm missing something obvious but, being contained and only having access to specific credentials is all nice and well but there is still an agent that orchestrates between the containers that has access to everything with one level of indirection.

That why I wrote "a VM or a separate host", "specific credentials" and "data provided to the agent must be considered compromised or leaked".

I should have added, "and every data returned by the agent must be considered harmful".

You should not trust anything done by an agent on the behalf of someone and certainly not giving RW access to all your data and credentials.

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

#725

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…

Same here, I'm slowly leaning towards your route as well. I've been building my own custom tooling for my agents to use as I come up with issues i need to solve in a better way.

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

#726

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".

Even if hordes of humanoids with “ice” vests start walking through the streets shooting people, the average American is still not going to wake up and do anything

The average HNer may be at least as bad as the average American on this axis. Lots of big tech apologist and might makes right takes here. Also a lot of "no big deal" style downplaying of risks and externalities

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

#727
post #494

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…

So human become just a provider of those 6 digits code ? That’s already the main problem i have with most agents: I want them to perform a very easy task: « fetch all recepts from website x,y and z and upload them to the correct expense of my expense tracking tool ». Ai are perfectly capable of performing this. But because every website requires sso + 2 fa, without any possibility to remove this, so i effectively hav…

2fa, except its 0 factors instead of two?

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

#728

Earlier quoted context omitted.

Any suggestions for a specific claw to run? I tried OpenClaw in Docker (with the help of your blog post, thanks) but found it way too wasteful on tokens/expensive. Apparently there's a ton of tweaks to reduce spent by doing things like offloading heartbeat to a local Ollama model, but was looking for something more... put together/already thought through.

The pattern I found that works ,use a small local model (llama 3b via Ollama, takes only about 2GB) for heartbeat checks — it just needs to answer 'is there anything urgent?' which is a yes/no classification task, not a frontier reasoning task. Reserve the expensive model for actual work. Done right, it can cut token spend by maybe 75% in practice without meaningfully degrading the heartbeat quality. The tricky part…

Maybe I’m out of touch but why do you need an LLM to decide if there’s any work to be done? Can’t it just queue or schedule tasks? We already have technology for that that doesn’t require an LLM.

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

#729
post #604

Earlier quoted context omitted.

The creator has an estimated net worth of $50 million to $200 million prior to Open AI hiring him. If you listen to any interviews with him, doesn't really seem like the type of person who's driven by money and I get the impression that no matter what OpenAI is paying him, his life will remain pretty much unchanged (from a financial perspective at least). He also still talks very fondly about Claude Code and openly a…

You're telling me that a person that's greedy enough to have a net worth of several tens of millions doesn't care about money? Pull the other one, it's got bells on.

I didn't say he didn't care about money, I just don't think that's his main driver, especially since he's already set for life. He spent 10 years building a company around a genuinely valuable product that just about everyone was using and, yeah, it made him rich.

I think "I'm going to keep the money I made from the company I spent 10 years building" and "I'm not going to lie about the coding tools to try and court a deal with OpenAI" aren't contradictory values. If anything, after hearing him talk for a while, I think it's way more believable that he switched from CC to Codex because Anthropic sent lawyers after him over the ClawdBot name than because of an OpenAI deal.

Post reply on HN