I use the same analogy explaining to people what my meds do. They’re a catalyst in that they lower the activation energy of doing anything other than doomscrolling
Another happy aerospace here! IMO it does a great job with barely any configuration required (the default config works great, I have barely tweaked it over years of use), that said I’m not exactly power user of tiling WMs, I have one app per workspace 90% of the time
I don’t understand the screenshot, the “attacker” sent that to customers? Or Delve created this screenshot as a dramatic reenactment? The post is not clear
This reminded me of ViperGPT[1] from a couple of years ago, which is similar but specific to vision language models. Both of them have a root llm which given a query produces a python program to decompose the query into separate steps, with the generated python program calling a sub model. One difference is this model has a mutable environment in the notebook, but I'm not sure how much of a meaningful difference that is.