EMA-AI-L protocol that turns your prompt into AI slop during transit, but contains a header with the original prompt so the recipient gets your actual message without bullshit attached.
This is called an TLDR
I see this as an unambiguous win, if it actually works as shown.
The important messages are conveyed, and the dick-measuring about who can seem the most interactive and professional gets derailed.
I told this story before. I was migrating an old system to a new one and we discovered that we were still sending faxes to some companies. Our system would create a PDF and send to a server that was connected to a phone line. So we called those companies to ask if we could find another way to send the documents. We learned that they too had a server with a software that would receive the fax and transform it in a PDF.
I work at a bank and it’s mind boggling how often I encounter systems very similar to this. A signed PDF isn’t good enough but send it via fax and suddenly it’s secure 🙄
I worked at an MSP for years and had clients who would send it back and forth that way to each other. The most common were medical practices, but banking wasn’t far behind.
Fax was considered secure because you could lock up the fax machine physically.
My favorite setup was a medical practice that dealt with stomach issues, including colon cancer, and their neighbor in the same building who was a pathology lab. They both had the PDF to fax and fax to PDF servers set up to send back and forth when someone could just walk 50 feet and hand over paperwork.
And I’m over here just sending the bulletpoint unaided by AI. That must be why I can’t get a raise.
The question is, how different is the original bullet point to the end one
This is the inverse of data compression.
I plan to hold a relatively informal talk about declarative macros in Rust at $DAYJOB and the colleague who organizes that used an LLM to write the invitation flavor text.
I don’t hate it for that. It does some text formatting with emojis and whatnot, which is decent enough. It does have information about declarative macros, so it can throw in some rough ideas what listeners can expect, like reduced boilerplate.
What I certainly like less is that it sounds like the most bombastic salesperson, and of course doesn’t know what my talk will actually be about, so it just promises everything.Including some straight-up non-sense, like apparently I’ll show folks how to use declarative macros to “improve performance”. That genuinely had us wondering, if that’s possible. I’m guessing, you could theoretically pre-compute a value at compile-time, but them being declarative macros, you’d have to do horrid constructs, like basic addition becomes the equivalent of
if a==3 && b==5 then 8. I will most definitely not show that.
My best guess is that it saw that it’s about Rust, so it just threw in “performance” somewhere. 🫠Well, and of course, it repeats itself and writes lots of empty phrases. The text for the invitation is almost as long as my notes for the talk…
This is boomer humor style, but I like it. I got a good laugh.
