This is very well put, and captures my feelings on it. I take it as disrespect that someone would have any expectation for me to read something they can’t be bothered to write. LinkedIn is a great example - my entire professional network is just spamming at this point, which drowns out others that DO put in any effort.

For structured outputs like that wouldn’t it be better to get the LLM to create a script to repeatably make the translation?

I played around with it, but the configuration seems bloated and finicky, and the permissions were concerning. It was a pain getting it to work with a local model, which is clearly an afterthought. I thought the WhatsApp interface was clever, and I plan on stealing that idea, but also exposes a pretty serious attack vector, and the thought of it running with any kind of exposure or permissions on a system with my Apple ID was a bit terrifying. A sandboxed version probably couldn’t do all the interesting things, but without sandboxing this thing could probably ruin your life. I promptly uninstalled it, but I did take a few ideas away.

Such bad behavior on the back button - it’s such a shabby trick, and makes me think less of any site that pulls that.

My partner suffers from migraines and also suffered a traumatic brain injury in a car accident. I got her to try glp-1 based on some of the research I’d been reading…and it has been an absolute game changer.