Hacker News Reader

Comment by flashblaze | Hacker News Reader

I believe the thing which makes OpenClaw interesting is you can just ask it to do these things and it just does. Rather than you having to write these scripts. I understand with LLMs, writing these scripts would now be trivial, but I believe this is even more convenient.

View on HN

Yeah, that's absolutely a real phenomenon, but I don't think it's especially OpenClaw-specific: I have lots of folders that are just collections of instructions and scripts that have mostly started with a prompt, and that I run sandboxed agents over. Previously I'd have considered automating them, but now it's just "fire up sandbox in a project folder, let the tool build itself". I wrote about this a bit here: https://sgnt.ai/p/the-software-i-stopped-writing/

At least writing scripts you know what it will and won’t do, with open claw it will probably do what you want and maybe won’t do anything you don’t want.

You can check the scripts and cronjobs, als ask it to summarize the scripts actions (using another agent/model if you want). All in all, LLMs are not 100% trustworthy but generally things go as intended.

“Generally” I am not anti ai in any way but I do worry people will end up in trouble by giving things like ai agents too much fredom

Ah yes people get into trouble in all sorts of ways.

I have heard some stories about people's clawbot doing things like deleting their entire email inbox or buying random shit with their credit cards. it's difficult to tell how many of those stories are real or if they were just stories that would be funny.

Reply on news.ycombinator.com