logoalt Hacker News

Someone1234yesterday at 6:56 PM2 repliesview on HN

I think the point you're making is fully correct, so consider this a devil's advocate argument...

People claim, you can use Claw-agents more safely while getting some of the benefits, by essentially proxying your services. For example on Gmail people are creating a new Google accounts, forwarding email via rule, and adding access to their calendar via Google's Family Sharing. This allows the Claw agent to read email, access the calendar, but even if you ask it to send an email it can only send as the proxy account, and it can only create calendar appointments then add you as an attendee rather than destroy/altering appointments you've made.

Is the juice worth the squeeze after all that? That's where I struggle. I think insecure/dangerous Claw-agents could be useful but cannot be made safe (for the logical fallacy you pointed out), and secure Claw-agents are only barely useful. Which feels like the whole idea gets squished.


Replies

sfdlkj3jk342atoday at 2:56 AM

> I think insecure/dangerous Claw-agents could be useful but cannot be made safe

Isn't it a question of when they will be "safe enough"? Many people already have human personal assistants, who have access to many sensitive details of their personal lives. The risk-reward is deemed worth it for some, despite the non-zero chance that a person with that access will make mistakes or become malicious.

It seems very similar to the point when automated driving becomes safe enough to replace most human drivers. The risks of AI taking over are different than the risks of humans remaining in control, but at some point I think most will judge the AI risks to have a better tradeoff.

show 1 reply
jychangyesterday at 8:14 PM

We already have this concept. It’s called user accounts.

Your Gmail account vs my Gmail account. Your macOS account vs my macOS account.

Yes, I can spam you from my Gmail. Yes, I can use sudo on my Mac and damage your account. But the impact is by default limited.

The answer is to just treat assistants as a different user profile, use the same sharing mechanisms already developed (calendar sharing, etc), and call it a day.