Live data from Hacker News

Claws are now a new layer on top of LLM agents

twitter.com

701–710 of 1001 posts

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

#701
post #231

I don't understand the mac mini hype. Why can it not be a vm?

The question is: what type of mac mini. If you go for something with 64G + +16 cores, it's probably more than most laptop so you can run much bigger models without impacting your job laptop.

64GB Mac Mini is easily in the $2000 territory. At that point you might as well just buy a DGX Spark and get proper CUDA/Linux support.

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

#702
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…

!!DO NOT DO THIS!!

You can use 1password and 1password cli to give it mfa access and passwords at its leisure.

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

#704
post #619

Earlier quoted context omitted.

What is there to be furious about?

Managers will be starting to ask for claws in the development flow, claws for automation, etc. Another flashy trend everyone will have to endure because an influencer is hyping the tech. It happened in 2024/2025. Every manager demanding use of "vibe coding", because they bought the lie that is what everyone is doing and is the best thing since sliced bread and whatnot. Karpathy comes up with a new shit to hype, and e…

Well said. Remember MCPs?

I don't.

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

#706
post #604

Earlier quoted context omitted.

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.

Oh, the good old modest selfless millionaire fairytale to inspire modest selfless zeronaires! Never fails.

He sounds greedy as fuck. He speed ran buggy POS to sell to model co? Obvious as day what is there to see?

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

#707
I've been making digital agents since the GPT-3 API came out. Optionally fully local, fully voiced, animated, all of that. Even co-ran a VC funded company making agents, before a hostile takeover screwed it all up. The writing has been on the wall for years about where this was headed.

I have been using and evolving my own personal agent for years but the difference is that models in the last year have suddenly become way more viable. Both frontier and local models. I had been holding back releasing my agents because the appetite has just not been there, and I was worried about large companies like X ripping off my work, while I was still focused on getting things like security and privacy right before releasing my agent kit.

It's been great seeing claws out in the wild delighting people, makes me think the time is finally right to release my agent kit and let people see what a real personal digital agent looks like in terms of presentation, utility and security. Claws are still thinking too small.

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

#708
post #522

Earlier quoted context omitted.

once the models get smart enough, you wont need n8n, they will just do the workflow without it needing to be specified. this is coming pretty soon

Probably but with n8n you can keep a trace of execution no?

They’re raising tens and hundred of billions.

If you and others want that feature, and they think that’ll keep you using and paying, they’ll build it.

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

#709
post #512

Earlier quoted context omitted.

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 passwo…

In my opinion people are fixating a little too much over the automation part, maybe because most people don't have a lot of experience with delegation... I mean, a VP worth his salt isn't generally having critical emails drafted and sent on his behalf without his review. It happens with unimportant emails, but with the stuff that really impacts the business far less often, unless he has found someone really, really g…

You might be right, but not for long. Once my agent is interacting directly with your agent (as opposed to doing drafts of your work on your behalf), expectations will shift to 24/7 operation.

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

#710

I still dont understand the hype for any of this claw stuff

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.

Running constantly = more revenue for openAI.
Post reply on HN