This is just blogspam, right? The author even brags about hitting the HN front page in such a short amount of time, in a previous post. All he talks about is his agent (that we are supposed to "know"? arrogant). Not a lot of discussion from him about his results.
That's pretty interesting. There have been a couple of occasions now where I wanted to forward emails to my agent. Going to take a deeper look at that.
Yeah, I have some boxes with some actions like: match positions in email to my skill set, make top 10, send on Telegram, and one box makes attachments out of emails and forwards to book keeping.
I found it kinda interesting, even if it could have been written by an AI with extensive prompting on how to sound human.
I've been pondering a conceptually similar approach for keeping slop out of important git repos. The agent has its own slop repo that it can slop up as much as it likes for R&D, and then I transcribe what works into my clean repo (ensuring I understand it, in the process).
7 comments
[ 0.22 ms ] story [ 21.6 ms ] threadIn general I'd like more services to maintain a wall between me and agent, but then again, we can also let the agents build it.
[0] https://www.agentmail.to/
Guy (micro)blogs that his imaginary friend now has a data structure that apparently mimics a calendar and possibly exposes an ical feed.
Good for them, but why does the internet need to know that?
I've been pondering a conceptually similar approach for keeping slop out of important git repos. The agent has its own slop repo that it can slop up as much as it likes for R&D, and then I transcribe what works into my clean repo (ensuring I understand it, in the process).