[pyridines]

It is ridiculously more expensive and complicated under the hood, technically, but to the user, the sheer convenience of being able to text the computer "hey, when I get an email like X, inform Y and do Z" and that's it, you're done, is unmatched.

[latexr]

What about the convenience of having your whole inbox deleted?

https://www.pcmag.com/news/meta-security-researchers-opencla...

Maybe OpenClaw was just practicing a really aggressive form of Inbox Zero.

[BeetleB]

So ... don't give it write access to your email?

As I said elsewhere, complaining about this is like complaining that rm can let you delete your hard drive.

It's a tool. Learn how to use it.

[Volundr]

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.

[BeetleB]

Don't give it access to your email then. I haven't. Plenty of other uses for it!

[hungryhobbit]

Use this software, it's amazing, it will change your life!"

"Oh but don't use it for A, or B, or C (even though it says to use it for A, B, and C): it will ruin your life"

[BeetleB]

Yes and yes!

A spouse can be amazing, or can destroy your life. Would you use that as an argument against marriage?

[Volundr]

Like what?

[SyneRyder]

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.

[theshrike79]

It's all tradeoffs and threat models.

You can prevent yourself from getting spam by not having an email account. But it's the nuclear option.

I'm fine with a system that can just read mail - and I already built one of those. I personally never send emails anyway so it's not an issue for me.

[Volundr]

So what do you do with your OpenClaw instance that has read-only access to your email and no Internet access?

[theshrike79]

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.

[theshackleford]

> As I said elsewhere, complaining about this is like complaining that rm can let you delete your hard drive.

rm won't wipe my HDD on a whim whilst instructing it to do something totally different.

You pretending they are the same thing is disingenous.

[Kriev]

Bad take.

You can rm -rf your entire hard drive, but you can't blame rm for it, it's you who did it, maybe because you don't know, or a mistake, doesn't matter.

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.

Can't expect deterministic outcomes out of a statistical model.

At it's current state its a wildcard, sure you can build guard rails, reduce permissions, but it's still a wildcard.

Let's not kid ourselves saying is just a skill issue.

[BeetleB]

> 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.

[latexr]

> 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.

[BeetleB]

> 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.

Also: Is anyone telling you to use it?

[skeledrew]

Worth the risk.

[jcgl]

Sure, that’s an interface that’s better for many users and use-cases.

However, it seems better if you could, as much as is possible, move the AI stuff from runtime to “compile time.”

Instead of having the AI do everything all the time, have AI configure your Zapier (or whatever) on your behalf. That way you can (ideally) get the best of both worlds: the reliability and predictability of classical software, combined with the fuzzy interface of LLMs.

[BeetleB]

> Instead of having the AI do everything all the time, have AI configure your Zapier (or whatever) on your behalf.

That is what many use OpenClaw for! The AI assistant will happily recommend existing services and help you (or itself, if you let it), set it up.

(In theory. In practice, it often does a poor job).

The appeal of OpenClaw is I don't need to go research all these possible solutions for different problems. I just tell it my problem and it figures it out.

Yesterday I told it to monitor a page which lists classes offered, and have it ping me if any class with a begin date in March/April is listed. This is easily scriptable by me, but I don't want to spend time writing that script. And modifying it for each site I want to be notified for. I merely spoke (voice, not text) to the agent and it will check each day.

(Again, it's not that reliable. I'm under no illusion it will inform me - but this is the appeal).

[samusiam]

But literally any decent agent can recommend existing services and help you set them up. And even help you help them set the services up for you. I do this with Claude all the time.

[skeledrew]

That's still too much work. Someone would have to make like an OpenClaw wizard that protectively offers to set all that stuff up. So the potential OpenClaw user can then, on running for the first time, be guided through the setup of whatever they'd like to get connected. And "setup" here means a short description of X and a "Connect? (y/n)" prompt. Anything more and you start losing people.

[jbellis]

yes. in a similar vein, we're seeing that get standardized in coding agents as "don't have the agent use tools directly, have the agent write code to call the tools"

[beepbooptheory]

Sometimes I reflect on all the metaphorical forests that have burned because a certain person at the right time only knew so much about how to use Excel, or the inbox rules of their MUA, or being totally unaware of the incredible power of macros of all sorts.

Like if you could just sit someone down for 30 minutes and show a few "power user" things, you will have truly taught her to fish for a lifetime. But it can go so unaddressed, and people's careers are built on these small ignorances.

I've cancelled everything at this point and just call Emacs my "special agential assistant," it makes me still sound in-the-know, and most of the time no one knows the difference!

"Convenience" in this context is laziness; "productivity" and "efficiency" is for management and bosses. We don't need to be our own bosses, I want to be free from such things as an individual. I want to be capable, be maybe almost "cool." Its sad to see a whole generation turn into such product dorks!

"Oh please read my email for me Mr. AI!"