Comment by teeray
1 day ago
> This demo uses AI to read emails instead of write them
LLMs are so good at summarizing that I should basically only ever read one email—from the AI:
You received 2 emails today that need your direct reply from X and Y. 1 is still outstanding from two days ago, _would you like to send an acknowledgment_? You received 6 emails from newsletters you didn’t sign up for but were enrolled after you bought something _do you want to unsubscribe from all of them_ (_make this a permanent rule_).
I have fed LLMs PDF files, asked about the content and gotten nonsense. I would be very hesitant to trust them to give me an accurate summary of my emails.
One of our managers uses Ai to summarize everything. Too bad it missed important caveats for an offer. Well, we burned an all nighters to correct the offer, but he did not read twenty pages but one...
I don't know if this is the case but be careful about shielding management from the consequences of their bad choices at your expense. It all but guarantees it will get worse.
15 replies →
Did he pull all nighters to fix it? If not, it wasn't "too bad" for him. I doubt he'll change his behavior.
Where's the IBM slide about "a machine cannot be held accountable, therefore a machine should never make a management decision"?
Of course, often it's quite hard to hold management accountable either.
1 reply →
LLMs are terrible at summarizing technical emails where the details matter. But you might get away with it, at least for a while, in low performing organizations that tolerate preventable errors.
If I get a technical email I read it myself. The summary just needs to say technical email from X with priority Y about problem Z
This. LLMs seem to be great for 90+% of stuff, but sometimes, they just spew weird stuff.
I got an email from the restaurant saying "We will confirm your dinner reservation as soon as we can", and Apple Intelligence summarizing it as "Dinner reservation confirmed." Maybe it can not only summarize, but also see the future??
Well, at least it doesn’t make up words. The Portuguese version of Apple Intelligence made up “Invitaçāo” (think “invitashion”) and other idiocies the very first day it started working in the EU.
> LLMs are so good at summarizing that I should basically only ever read one email—from the AI
This could get really fun with some hidden text prompt injection. Just match the font and background color.
Maybe these tools should be doing the classic air gap approach of taking a picture of the rendered content and analyzing that.
What system are you using to do this? I do think that this would provide value for me. Currently, I barely read my emails, which I'm not exactly proud of, but it's just the reality. So something that summarized the important things every day would be nice.
Do you ever check its work?
What is the reason to unsub ever in that world? Are you saying the LLM can't skip emails? Seems like an arbitrary rule