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

31–40 of 1001 posts

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

#31

Post by mattlondon »

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 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, and a more permissive SI.

Not rocket science, but interesting.

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

#33

Post by tokenless »

bjackman wrote: post #25

Does anyone know a Claw-like that: - doesnt do its own sandboxing (I'll set that up myself) - just has a web UI instead of wanting to use some weird proprietary messaging app as its interface?

Openclaw!

You can sandbox anything yourself. Use a VM.

It has a web ui.

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

#35

Post by arrowsmith »

7777777phil wrote: post #20

Karpathy has a good ear for naming things. "Claw" captures what the existing terminology missed, these aren't agents with more tools (maybe even the opposite), they're persistent processes with scheduling and inter-agent communication that happen to use LLMs for reasoning.

He didn't name it though, Peter Steinberger did. (Kinda.)

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

#36

Post by nnevatie »

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?

That's it basically. I do not think running the tool in a container really solves the fundamental danger these tools pose to your personal data.

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

#37

Post by _pdp_ »

You can take any AI agent (Codex, Gemini, Claude Code, ollama), run it on a loop with some delay and connect to a messaging platform using Pantalk (https://github.com/pantalk/pantalk). In fact, you can use Pantalk buffer to automatically start your agent. You don't need OpenClaw for that.

What OpenClaw did is to show the messages that this is in fact possible to do. IMHO nobody is using it yet for meaningful things, but the direction is right.

Post reply on HN