Alessio Fanelli: belief

Transcript context

…The general philosophy is we ask for the least amount of permissions needed at any given moment. I don't think Slack, I could be mistaken, but I don't think Slack lets you request permissions for just one channel. But for example, for Google, obviously there are hundreds of scopes that you could require for Google. There's a lot of scopes. And sometimes it's actually painful to set up your Lindy because you're going to have to ask Google and add scopes five or six times. We've had sessions like this. But that's what we do because, for example, the Lindy email drafter, she's going to ask you for your authorization once for, I need to be able to read your email so I can draft a reply, and then another time for I need to be able to write a draft for them. We just try to do it very incrementally like that. Do you think OAuth is just overall going to change? I think maybe before it was like, hey, we need to set up OAuth that humans only want to kind of do once. So we try to jam-pack things all at once versus what if you could on-demand get different permissions every time from different parts? Do you ever think about designing things knowing that maybe AI will use it instead of humans will use it? Yeah, for sure. One pattern we've started to see is people provisioning accounts for their AI agents. And so, in particular, Google Workspace accounts. So, for example, Lindy can be used as a scheduling assistant. So you can just CC her to your emails when you're trying to find time with someone. And just like a human assistant, she's going to go back and forth and offer other abilities and so forth. Very often, people don't want the other party to know that it's an AI. So it's actually funny. They introduce delays. They ask the agent to wait before replying, so it's not too obvious that it's an AI. And they provision an account on Google Suite, which costs them like $10 a month or something like that. So we're seeing that pattern more and more. I think that does the job for now. I'm not optimistic on us actually patching OAuth. Because I agree with you, ultimately, we would want to patch OAuth because the new account thing is kind of a clutch. It's really a hack. You would want to patch OAuth to have more granular access control and really be able to put your sugar in the box. I'm not optimistic on us doing that before AGI, I think. That's a very close timeline.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.