← Back to context

Comment by teekert

3 hours ago

Yeah that's true, and in many cases the AI just sets up a cronjob and a script (and a mailbox, and an interface to telegram, and a reporting structure). But it's nice that in case of errors it handles the edge cases or it fixes the scripts. It can give the crontable over telegram, you can pause it for the holiday "Number one, pause all processing until further notice"...

But sure, it's not "rocket science", in fact, the skills to set it up indeed would probably help you set up the same scripts. It's just behind a chat interface.

It can be nice to say: "Add another minecraft world with the same user whitelist on port 25566" or "create a demo website for a home battery on domain claw.xxx.com". But it is indeed not very useful for me yet. I think the more access you give it, the more it can be like a PA, but I don't want it in my calendar/home assistant/paperless-ngx etc... yet... When I even get to this point I can see it being like my secretary ("Please get my incomes taxes statement from 2024", "Estimate this years income taxes from my invoices so far", "Plan appointment with ..." etc)

"Number one, pause all processing until further notice"...

Because OpenClaw (well, all AI) is well known for following instructions correctly.

https://au.pcmag.com/ai/116091/meta-security-researchers-ai-...

  • There are reasons to be careful indeed, but for me all instructions were followed nicely so far.

    Yesterday I had Claude (in CC) do a large number of changes to my codebase using a bash script, even though I was in planning mode and in claude.md it says: Always first list the steps you're going to take before execution. It apologized of course... But I know how LLMs can be. I take that into account.