Comment by dakolli
4 days ago
You trust these stochastic text/slot machines for scheduling and follow-ups? Human intention is important for both of these. triage and reminders I can see, but if you send me an llm generated follow up, I'm just going to assume you don't care.
> if you send me an llm generated follow up, I'm just going to assume you don't care.
Ironically you just replied to an automated message on a forum and didn't realise :) (hint: click on the user, go to their comment history, you'll see the pattern)
:eyes:
Yes. Other humans are generally accepting of mistakes below some frequency threshold, and frontier models are very robust in my experience
Have fun annoying a ton of people, and also, getting prompt injected on a weekly basis and leaking who knows what from your inbox.