681–690 of 1001 posts
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 read all 500+ comments at the time of writing and I don't understand. Something about something, with people saying something isn't a claw.
> Something about something, with people saying something isn't a claw.
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.
Claw is a terrible name for a basic product which is Claude code in a loop (cron job).
This whole hype cycle is absurd and ridiculous for what is a really basic product full of security holes and entirely vibe coded.
The name won’t stick and when Apple or someone releases a polished version which consumers actually use in two years, I guarantee it won’t be called “iClaw”
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?
Earlier quoted context omitted.
> Weirdly, he doesn’t care about the toxicity problems on Twitter/X either, > Yet he has the nerve to call HN toxic. That's not weird or paradoxical. They don't have to delineate every online platform they disagree with in order to criticize HN; "orange site bad" is a pretty common sentiment in my experience.
I hear about X being hateful but nobody wants to talk about how toxic BlueSky actually is. I had to stop going on there permanently. I dont think I have ever quit a social media platform as quickly and permanently as BlueSky.
Are people buying mac minis to run the models locally?
No they’re buying them as a home server. You can’t message your claw if your laptop lid is closed.
We got store-brand Claw before GTA VI. For real though, it's not that hard to make your own! NanoClaw boasted 500 lines but the repo was 5000 so I was sad. So I took a stab at it. Turns out it takes 50 lines of code. All you need is a few lines of Telegram library code in your chosen language, and `claude -p prooompt`. With 2 lines more you can support Codex or your favorite infinite tokens thingy :) https://github.c…
you need to add cron to have a claw
Earlier quoted context omitted.
There are a few qualitative product experiences that make claw agents unique. One is that it relentlessly strives thoroughly to complete tasks without asking you to micromanage it. The second is that it has personality. The third is that it's artfully constructed so that it feels like it has infinite context. The above may sound purely circumstantial and frivolous. But together it's the first agent that many people w…
Can you give some example for what you use it for? I understand giving a summary of what's waiting in your inbox but what else?
Now that could evolve and turn into a personal trainer keeping track of my progress.
What if I send it my heart rate. Etc. Prove I did it.
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…
Earlier quoted context omitted.
Extending your driver's license. Asking the bank for a second mortgage. Finding the right high school for your kids. The possibilities are endless. /s <- okay
Is this sarcasm? These all sound like things that I would never use current LLMs for.
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…
Until the agent decides that it's more efficient to fake an approval, and carries on...