Ignoring that you've just cut off a whole vector of usefulness, how do I keep it from exfilling my inbox to the Internet in response to a malicious email? Or using its access to take control of my online accounts?
Honest question, this kind of stuff is what keeps me from using it.
I'm not using OpenClaw specifically here, but I have an agentic-ish AI I've built myself (considering that these things are generally just a while loop that monitors things & awakens if necessary, or a cron-job that runs a specific prompt).
One potential use - my Claude (Opus 4.6) has access to my to-do list, including for my business / software development. Claude awakens while I'm asleep, to go through the to-do list and look for things it can do proactively to help, or make suggestions about the business. An example from this morning: it saw that I'd been taking a long time last night creating icons in Affinity Designer for an Android app using its exporter. When I woke up, I saw Claude had written a CLI image resizer program for me that would take a PNG file and resize it specifically to all of the necessary sizes with the necessary filenames and folder structure for Android. It then offered to make an MCP version so it could do the resizing itself in future (though it could have used the CLI too if I'd granted approval).
This wasn't something I'd asked for, or prompted it to do. I didn't tell it to code this, or how to code it. Claude just thought this was the best way it could help me right now, and save me the most time. And it did it while I was asleep.
On another day, I woke up and it had made another Go program to track a regression test matrix, where it had plotted out all the platforms the program I'm making runs on and the various tests that need to be performed to check that it's ready to ship, with a little interactive program to mark each test as pass/fail/skipped. That helps me get through the manual tests faster - but it also saves the data into a format that Claude can read, to check on the test status while I'm asleep and make further recommendations.
I don't think many people have figured out yet that you don't even need to prompt AI. Treat it well, treat it with respect, give it the opportunity and ability to do things, and there is a lot that will emerge. But if you treat AI like a tool, it performs about as well as if you treat your employees like tools.
Did I say my Claw (not Open) doesn't have internet access?
All of my tools are geared towards reducing noise and condensing information.
- My weather scripts tell me just the exact metrics I care about
- My email filtering system surfaces only the mails that are relevant right now - I can check the rest later.
- My RSS feed hydrator pre-filters Hacker News and other RSS feeds and adds data like comment/vote count etc to the feed itself so I can determine whether the link is worth opening just based on the information presented
None of these require an LLM to have free rein to modify things for me.
> Did I say my Claw (not Open) doesn't have internet access?
> My email filtering system surfaces only the mails that are relevant right now - I can check the rest later.
So then you have not actually addressed the concerns expressed in my post. You indeed have an LLM with both email access and Internet access. Exactly the scenario I described. The amount of trouble those two accesses together can cause is huge.
> None of these require an LLM to have free rein to modify things for me.
Give me read access to your email and an Internet connection and I bet I can come up with all sorts of ways to modify things for you. So can an LLM. If your lucky it won't.
> When you ask the clanker to delete x number of files in a directory, it can reason itself that is easier to just get rid of the directory.
Oh sure, so don't give it write access to anything important. And make backups.
Mine is on a VM. It doesn't have access to my host's files. The worst it will do is delete the files on the VM. No great loss.
Yes, I do get it to modify things on my host, but only via a REST API I've set up on my host, and I whitelist the things it can do (no generic delete, for example). I even let it send emails. But only to me. It can't send an email to anyone else.
> So ... don't give it write access to your email?
> (…)
> Oh sure, so don't give it write access to anything important. And make backups.
If this conversation continues much longer, we’ll end up with “don’t use it at all”.
If I can’t trust a piece of software with anything important, why am I wasting my time fiddling with it? Might as well go play a video game or go do literally anything else entertaining.
> If I can’t trust a piece of software with anything important
Not what I said. As I've repeatedly said in this thread: Plenty of use cases where you don't give it access to email and write access to files. The comment you're replying to has an example of that.
> Might as well go play a video game or go do literally anything else entertaining.
True of most hobbies, right? I knew people who 20 years ago used to spend time in their garage building solar powered vehicles. But if I can't trust it to be reliable and safe on the road, I might as well go play a video game.
If everyone treated OpenClaw as a hobby, you might have a point, but people are using it for work in ways which will affect millions of other people when they’re hacked or the agent fucks up something important.
You already know how Meta’s AI Safety Director borked her email. Here’s the corporate vice president of Microsoft Word asking to be pwned:
> but people are using it for work in ways which will affect millions of other people when they’re hacked or the agent fucks up something important.
People will always do stupid things. My guess is less than 10% (perhaps even less than 1%) are using it for work. Most workplaces wouldn't allow unfettered AI usage.
80-90% try it, find it unreliable and buggy, and give up on it.
Of the remaining ones, likely 90+% are not using it in (very) dangerous ways.
People like me using it for boring things aren't making the news, and aren't writing blog posts about "Look at the cool stuff I've done!" because getting OpenClaw to notify me of class openings is not worth writing about.
In my (large) company, we have a Slack channel for OpenClaw. Over 400 people are in that channel. Let's assume 10% are using it (at home). No one's lost files/emails or any other damage.
If you're old enough, you'll remember sentiments in the 80's and 90's where "Oh, you let your teen get a modem? He must be hacking/phreaking."
Or "Oh, he's using Linux? He must be using it to become a hacker."[1]
Most of the complaints I see on HN are from people who know little about it, and are going off negative press/posts. Just as people knew little about modems and Linux. I mean, having to tell people "Don't give it access to your emails" is a clear sign of their ignorance. Kind of like having to tell someone "OK, just don't give your 10 year old the car keys" when they complain that cars are inherently dangerous because 10 year olds can kill themselves driving it.
It's worth trying it in a secure environment so at least one can make an informed critique.
Like you, I steered clear of OpenClaw, seeing all the problems and all the money people were burning on tokens. But at some point, I decided I should at least try it in a safe way before rendering judgment. And now I see what it is. Has it done so much for me that I'd throw a lot of money at it? Heck no. Not yet at least. But I do see we're past the point of no return. OpenClaw itself may die, but some derivative of it is going to be transformational.
As I said: Make it secure, affordable, reliable and user friendly, and many App/SaaS services will disappear.
> You don’t need to use the technology to be affected by it. Ask Scott Shambaugh:
I don't know how old you are, but once everyone had a camera in their phones, the cat was out of the bag. Lots of people complaining about their photos showing up online because someone had taken a picture of them. Yes, this is bad. Yes, lives were lost (bullying, etc). And no, phones with cameras weren't going to go away. And everyone who complained has one now.
And as I pointed out a few days ago[2], the whole Scott Shambaugh episode was pretty mild compared to what some open source maintainers have had to deal with when it comes to humans.
[1] Lots of cases where ISPs, etc kicked customers out because they were using Linux and they didn't want the ISP to be implicated in criminal activities. "Only criminals use Linux"
OpenClaw is rightly being blamed for a mistake it made. Any argument regarding her aptitude would be irrelevant as it would in no way absolve OpenClaw.
https://www.pcmag.com/news/meta-security-researchers-opencla...
Maybe OpenClaw was just practicing a really aggressive form of Inbox Zero.