Why does everything related to AI have to have such awful names? It’s as if everything is named to be as annoying as possible.
Capitalizing on Rust hype?
Claws are now a new layer on top of LLM agents
801–810 of 1001 posts
Re: Claws are now a new layer on top of LLM agents
#802We 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
Fair enough. Is that all it takes? The heartbeat is only a few more lines of code. Cron made the code a few hundred lines instead of a few dozen so I didn't like that.
(Also, I think heartbeat.md can emulate Cron? Using an LLM to expensively and inefficiently emulate Cron sounds a lot more in line with the Claw philosophy, doesn't it? ;)
The neat part is that it can modify/upgrade/restart itself. So if you are missing any feature, you just complain and it adds it to itself. (And it does that more reliably than OC in my experience, because it's small enough to actually understand itself.)
Re: Claws are now a new layer on top of LLM agents
#803Earlier quoted context omitted.
It's not a perfect security model. Between the friction and all caps instructions the model sees, it's a balance between risk and simplicity, or maybe risk and sanity. There's ways I can imagine the concept can be hardened, e.g. with a server layer in between that checks for things like dangerous actions or enforces rate limiting
If all you're doing is telling an LLM to do something in all caps and hoping it follows your instructions then it's not a "security model" at all. What a bizarre thing to rely on. It's like people have literally forgotten how to program.
Thank you for saying this. I read this and was like: wtf?
Love agents, but the security risk is insane.
Re: Claws are now a new layer on top of LLM agents
#804I still don't understand what openclaw is or does and i've read the docs multiple times over. "Any OS gateway for AI agents across WhatsApp, Telegram, Discord, iMessage, and more. Send a message, get an agent response from your pocket. Plugins add Mattermost and more." "What is OpenClaw? OpenClaw is a self-hosted gateway that connects your favorite chat apps — WhatsApp, Telegram, Discord, iMessage, and more — to AI c…
you give an LLM control of your computer.
Yesterday I told it to make a website and it opened the browser, did a bunch of steps, (I did have to authenticate). But then it connected some html on my computer with a server with google sheets.
Consider its a massive security risk. You are giving it full access to everything your computer can do. (Potentially, you can limit stuff)
Re: Claws are now a new layer on top of LLM agents
#805Earlier quoted context omitted.
Is there a risk that the summary doesn't fully match the action that actually gets executed?
Side note: Just like with a human employee asking for permission to do something.
Except for the accountability if they screw up; and the human brain thinking through what they are doing.
Re: Claws are now a new layer on top of LLM agents
#806One 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…
Sounds like decision fatigue problem will hit rather quickly. Maybe after 5th or 10th time everything is good... And then it will happen anyway.
Re: Claws are now a new layer on top of LLM agents
#807Earlier quoted context omitted.
Reading some documentation to figure out a format is something you do once and takes you a few minutes. Are you a developer? Then this is something you probably do a couple times a day. Prompting the correct version will take longer and will leave you with much less understanding of the system you just implemented. So once it fails you don't know how to fix it.
I love that the posture is I have a problem I need you to fix haha. I don't need you to fix my problems. I'm reporting that the LLM-based solution beats the dogshit out of the old "become a journeyman on one of 11 billion bullshit formats or processes" practice.
I'm not trying to help you, I'm just wondering how the LLM actually helps you.
You don't need to become a journeyman at understanding a format, you just need to see a schema, or find an open source utility. I just can't comprehend the actual helplessness that a developer would have to experience in order to have to ask an LLM to do something like this.
If I were that daunted by parsing a standardized file format for a workflow, I would have to be experiencing a major burnout. How could I ever assume I could do any actual technical work if I'm overwhelmed by a parsing problem that has out-of-the-box solutions available.
Re: Claws are now a new layer on top of LLM agents
#808Earlier quoted context omitted.
It's not a perfect security model. Between the friction and all caps instructions the model sees, it's a balance between risk and simplicity, or maybe risk and sanity. There's ways I can imagine the concept can be hardened, e.g. with a server layer in between that checks for things like dangerous actions or enforces rate limiting
If all you're doing is telling an LLM to do something in all caps and hoping it follows your instructions then it's not a "security model" at all. What a bizarre thing to rely on. It's like people have literally forgotten how to program.
These people often never knew in the first place.
Re: Claws are now a new layer on top of LLM agents
#809Earlier quoted context omitted.
It's not just waiting for input, it has a heartbeat.md prompt that runs every X minutes. That gives it a feeling that it's always on and thinking.
That gives _you_ a feeling that it's always on. It still can't model time.
Or feeling things for that matter.
Re: Claws are now a new layer on top of LLM agents
#810Serious question for early adopters of Claws: what are you using them for? What things do you find them actually useful? Can you give examples of tasks where you actually save time and/or effort using them?
Farming interactions on twitter