I really don’t understand what it does. Is it just the equivalent of chron jobs but with agents?
Claws are now a new layer on top of LLM agents
691–700 of 1001 posts
Re: Claws are now a new layer on top of LLM agents
#692Earlier quoted context omitted.
> it's the first agent that many people who usually avoid AI simply LOVE. Not arguing with your other points, but I can't imagine "people who usually avoid AI" going through the motions to host OpenClaw.
My work partner set it up on telegram for himself and his wife and she uses it constantly. He was very surprised.
[flagged]
Re: Claws are now a new layer on top of LLM agents
#693One 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…
Yes, all caps, that should do it!
The OTP is required for the tool to execute. The all caps message just helps make sure the agent doesn't waste time/tokens trying to execute without it.
Re: Claws are now a new layer on top of LLM agents
#694One 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…
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…
In my opinion people are fixating a little too much over the automation part, maybe because most people don't have a lot of experience with delegation... I mean, a VP worth his salt isn't generally having critical emails drafted and sent on his behalf without his review. It happens with unimportant emails, but with the stuff that really impacts the business far less often, unless he has found someone really, really great
Give me a stack of email drafts first thing every morning that I can read, approve and send myself. It takes 30 seconds to actually send the email. The lion's share of the value is figuring out what to write and doing a good job at it. Which the LLMs are facilitating with research and suggestions, but have not been amazing at doing autonomously so far
Re: Claws are now a new layer on top of LLM agents
#695> I'm definitely a bit sus'd to run OpenClaw specifically - giving my private data/keys to 400K lines of vibe coded monster that is being actively attacked at scale is not very appealing at all.
Ignore turning lose agents on the internet that are capable of pulling in unchecked data into it's context window.
Wild times.
Re: Claws are now a new layer on top of LLM agents
#696Earlier quoted context omitted.
Any suggestions for a specific claw to run? I tried OpenClaw in Docker (with the help of your blog post, thanks) but found it way too wasteful on tokens/expensive. Apparently there's a ton of tweaks to reduce spent by doing things like offloading heartbeat to a local Ollama model, but was looking for something more... put together/already thought through.
The pattern I found that works ,use a small local model (llama 3b via Ollama, takes only about 2GB) for heartbeat checks — it just needs to answer 'is there anything urgent?' which is a yes/no classification task, not a frontier reasoning task. Reserve the expensive model for actual work. Done right, it can cut token spend by maybe 75% in practice without meaningfully degrading the heartbeat quality. The tricky part…
It seems to me like it would be a rather useful exercise to have the smaller model make the routing decision, and below certain confidence thresholds, it sends it to a larger model anyways. Then have the larger model evaluate that choice and perhaps refine instructions.
Re: Claws are now a new layer on top of LLM agents
#697I wonder how the internet would have been different if claws had existed beforehand. I keep thinking something simpler like Gopher (an early 90's web protocol) might have been sufficient / optimal, with little need to evolve into HTML or REST since the agents might be better able to navigate step-by-step menus and questionnaires, rather than RPCs meant to support GUIs and apps, especially for LLMs with smaller contex…
Yesterday IMG tag history came up, prompting a memory lane wander. Reminding me that in 1992-ish, pre `www.foo` convention, I'd create DNS pairs, foo-www and foo-http. One for humans, and one to sling sexps. I remember seeing the CGI (serve url from a script) proposal posted, and thinking it was so bad (eg url 256-ish character limit) that no one would use it, so I didn't need to worry about it. Oops. "Oh, here's a s…
sexps?
Re: Claws are now a new layer on top of LLM agents
#698[dead]
Re: Claws are now a new layer on top of LLM agents
#699Why mac mini instead of something like a raspberry pi? Aren't thede claw things delegating inference to OpenAI, Antropic etc.?
Easy enough for average Joe to set up. Can run several Chrome tabs. pi cannot
If you cannot configure a Raspberry Pi, you're probably not the sort of person that should be connecting agents to your local network.
Re: Claws are now a new layer on top of LLM agents
#700Earlier quoted context omitted.
Yes, all caps, that should do it!
The OTP is required for the tool to execute. The all caps message just helps make sure the agent doesn't waste time/tokens trying to execute without it.
Why not just wrap the tool so that when the LLM uses it, the wrapper enforces the OTP? The LLM doesn't even need to know that the tool is protected. What is the benefit of having the LLM enter the OTP?