Why mac mini instead of something like a raspberry pi? Aren't thede claw things delegating inference to OpenAI, Antropic etc.?
A Mac allows it to send iMessage and access the Apple ecosystem.
Claws are now a new layer on top of LLM agents
41–50 of 1001 posts
Re: Claws are now a new layer on top of LLM agents
#42I read [and comment on] two influencers maintaining their circles
Re: Claws are now a new layer on top of LLM agents
#43I wonder how long it'll take (if it hasn't already) until the messaging around this inevitably moves on to "Do not self-host this, are you crazy? This requires console commands, don't be silly! Our team of industry-veteran security professionals works on your digital safety 24/7, you would never be able to keep up with the demands of today's cybersecurity attack spectrum. Any sane person would host their claw with us!"
Next flood of (likely heavily YC-backed) Clawbase (Coinbase but for Claws) hosting startups incoming?
Re: Claws are now a new layer on top of LLM agents
#44Karpathy 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.
Why do we always have to come up with the stupidest names for things. Claw was a play on Claude, is all. Granted, I don’t have a better one at hand, but that it has to be Claw of all things…
Re: Claws are now a new layer on top of LLM agents
#45Re: Claws are now a new layer on top of LLM agents
#46Re: Claws are now a new layer on top of LLM agents
#47Who is Andrej Karpathy?
[flagged]
I bet they feel so, so silly. A quick bit of reflection might reveal sarcasm.
I'll live up to my username and be terribly brave with a silly rhetorical question: why are we hearing about him through Simon? Don't answer, remember. Rhetorical. All the way up and down.
Re: Claws are now a new layer on top of LLM agents
#48So 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,…
Cron would be for a polling model. You can also have an interrupts/events model that triggers it on incoming information (eg. new email, WhatsApp, incoming bank payments etc).
I still don't see a way this wouldn't end up with my bank balance being sent to somewhere I didn't want.
Re: Claws are now a new layer on top of LLM agents
#49I wonder how long it'll take (if it hasn't already) until the messaging around this inevitably moves on to "Do not self-host this, are you crazy? This requires console commands, don't be silly! Our team of industry-veteran security professionals works on your digital safety 24/7, you would never be able to keep up with the demands of today's cybersecurity attack spectrum. Any sane person would host their claw with us…
In a sense, self-hosting it ( and I would argue for a personal rewrite ) is the only way to limit some of the damage.
Re: Claws are now a new layer on top of LLM agents
#50So 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,…
Definitely interesting but i mean giving it all my credentials feels not right. Is there a safe way to do so?