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

11–20 of 1001 posts

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

#11

Post by hoss1474489 »

It’s a slow burn, but if you keep using it, it seems to eventually catch fire as the agent builds up scripts and skills and together you build up systems of getting stuff done. In some ways it feels like building rapport with a junior. And like a junior, eventually, if you keep investing, the agent starts doing things that blow by your expectations.

By giving the agent its own isolated computer, I don’t have to care about how the project gets started and stored, I just say “I want ____” and ____ shows up. It’s not that it can do stuff that I can’t. It’s that it can do stuff that I would like but just couldn’t be bothered with.

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

#12

Post by phil21 »

aalam wrote: post #3

[flagged]

It’s really just easier integrations with stuff like iMessage. I assume easier for email and calendars too since that’s a total wreck trying to come up with anything sane for Linux VM + gsuite. At least has been from my limited experience so far.

Other than that I can’t really come up with an explanation of why a Mac mini would be “better” than say an intel nuc or virtual machine.

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

#13

Post by steve1977 »

phil21 wrote: post #12
aalam wrote: post #3

[flagged]

It’s really just easier integrations with stuff like iMessage. I assume easier for email and calendars too since that’s a total wreck trying to come up with anything sane for Linux VM + gsuite. At least has been from my limited experience so far. Other than that I can’t really come up with an explanation of why a Mac mini would be “better” than say an intel nuc or virtual machine.

Unified memory on Apple Silicon. On PC architecture, you have to shuffle around stuff between the normal RAM and the GPU RAM.

Mac mini just happens to be the cheapest offering to get this.

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

#14

Post by cromka »

steve1977 wrote: post #13
phil21 wrote: post #12

Earlier quoted context omitted.

It’s really just easier integrations with stuff like iMessage. I assume easier for email and calendars too since that’s a total wreck trying to come up with anything sane for Linux VM + gsuite. At least has been from my limited experience so far. Other than that I can’t really come up with an explanation of why a Mac mini would be “better” than say an intel nuc or virtual machine.

Unified memory on Apple Silicon. On PC architecture, you have to shuffle around stuff between the normal RAM and the GPU RAM. Mac mini just happens to be the cheapest offering to get this.

But the only cheap option is 16GB basic tier Mac Mini. That's not a lot of shared memory. Proces increase bery quickly for expanded memory models.

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

#15

Post by steve1977 »

cromka wrote: post #14
steve1977 wrote: post #13

Earlier quoted context omitted.

Unified memory on Apple Silicon. On PC architecture, you have to shuffle around stuff between the normal RAM and the GPU RAM. Mac mini just happens to be the cheapest offering to get this.

But the only cheap option is 16GB basic tier Mac Mini. That's not a lot of shared memory. Proces increase bery quickly for expanded memory models.

I meant cheap in the context of other Apple offerings. I think Mac Studios are a bit more expensive in comparable configurations and with laptops you also pay for the display.

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

#16

Post by WA »

cromka wrote: post #14
steve1977 wrote: post #13

Earlier quoted context omitted.

Unified memory on Apple Silicon. On PC architecture, you have to shuffle around stuff between the normal RAM and the GPU RAM. Mac mini just happens to be the cheapest offering to get this.

But the only cheap option is 16GB basic tier Mac Mini. That's not a lot of shared memory. Proces increase bery quickly for expanded memory models.

Why though? The context window is 1 millions token max so far. That is what, a few MB of text? Sounds like I should be able to run claw on a raspberry pi.

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

#17

Post by arjie »

The openclaw rough architecture isn’t bad but I enjoyed building my own version. I chose rustlang and it works like I want. I made it a separate email address etc. and Apple ID. The biggest annoyance is that I can’t share Google contacts. But otherwise it’s great. I’m trying to find a way to give it a browser and a credit card (limited spend of course) in a way I can trust.

It’s lots of fun.

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

#19

Post by YetAnotherNick »

What is anyone really doing with openclaw? I tried to stick to it but just can't understand the utility beyond just linking AI chat to whatsapp. Almost nothing, not even simple things like setting reminders, worked reliably for me.

It tries to understand its own settings but fails terribly.

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

#20

Post by 7777777phil »

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.

Post reply on HN