HN Explorer

Ask HN: Why don't email apps use AI to avoid sending to the wrong person?

2 points by eternityforest ↗ HN
Seems like most everyone has experienced this. We have the confirmation button, but that only helps a little, it eventually gets done without thinking.

AI could use some metrics to detect how likely it is that you have the correct sender. If you don't talk to them often, or if the list of topics discussed contains something new you haven't sent that person, it could display extra warnings.

It's simple enough that it could even be done purely with on-device local AI.

At the very least, the confirmation screen should always show a summary, with the profile pictures of all recipients, and thumbnails of any attachments.

2 comments

[ 190 ms ] story [ 173 ms ] thread
8organicbits
I've seen the reverse, Gmail suggesting additonal people I may want to include, although I don't think that's based on the message body. I personally wouldn't want more server-side content scanning, nor would I want the bloat of it running in my browser.
eternityforest
I wonder if they avoid this specifically because it would make it immediately obvious how much they are able to scan, rather than ad targeting, which just gives a vague sense that they know everything but not in sharp focus like that.

I personally care far less about what Google can see than about what I might accidentally send, it hasn't happened to me, but it could be bad to send a work email to a random person, someone could even be fired if there was a trade secret.

But I can see it upsetting more privacy minded consumers if it wasn't done very carefully, with a big annoying "This was generated in your browser and we do not scan message content" notice.