I have heard a similar sentiment at a conference recently, AI (i.e. LLMs) are "a new user group" apparently? It's very weird to me, a bike lane is not designed literally for the bike but for people to get where they are going safely.
As I understand it, cutting through the marketing blabla, It's for an agent (as an LLM-in-a-loop) to iteratively improve its own prompt based on initial instructions, thereby saving you tokens and time when writing prompts.
Ofc the LLM can still ignore relevant ones, load the wrong one etc
They do count when they are used, but the idea is that they are used only when relevant so if you compare this to sending all the instructions all the time you'll end up saving tokens.
Be my guest ^^
And also, "bike-first design" seems little more than an excuse for people in power to do "bike-only design" and then decide what the bike needs, like "go as fast as you want" and "not paying attention to pedestrians".
Cool! I think about it a lot in the context of UI design (as a kind of specification), I have been meaning to riff on that myself as well
DON DRAPER, wearing a Changshan: if we want to sell this revolution as being truly universal under Heaven, we need to make inroads with the fairer sex… how about “women hold up half the sky”
MAO, sucking on his teeth: god damn it gweilo you’ve done it again.
This is a very good, in-depth post that aligns very well with what I also observe in Software currently!
Also chuffed that the Borges I suggested made it in, very cool!
Well I think you could add shell scripts and the like, it's just very rarely done apparently. Also, I would like do make it very I clear I do NOT recommend downloading and running random shell scripts on one's computer if one does not understand what they are doing.
Love this, when stuff like this is brought up, I always think about the map that is as big as the empire in this short piece by Borges: neilgreenberg.com/ao-quote-bor...
