This is how we were building SuperDuper ~10 months ago. Today? The apps we're building at Inertia today consider what users are trying to do and where they get stuck, and propose their OWN improvements. It's wild to see an app keep a list of it's own shortcomings to work on later.
I'm now building an "improvements" feature into all of my personal vibecoded applications: a freeform text input that's hooked up to an agent that yolo implements whatever is submitted.
It's an interesting experience -- the activation energy barrier to sanding any rough edge or implementing any new feature becomes extremely low. Someone else who uses one of the applications I created has already implemented 150 improvements over the course of a few days. This pattern feels like a new kind of tool -- liquid software? -- and every application that doesn't have this feature now has a slightly rigid and anachronistic flavor. Why can't I just tell it how I want it to be different?
Now, it's not obvious to me how this pattern can or should scale. Does it become unmaintainable after a while? (Maybe model intelligence improvement outstrips my feature appetite such that it's fine?) How does collaborative software work in this model? Can software designed this way be secure and reliable?
Whatever the larger questions about broader deployment, it definitely works great in a personal context. It reminds me a little of the visions of Lisp/Lisp machines, Smalltalk, and HyperCard -- systems that the user can take control of and modify. Those visions never quite worked, though: the vast majority of software today is not end-user modifiable in any useful way. So, while this "liquid" affordance is a very small touch, the way it changes one's relation to the software feels a bit transgressive and empowering in a Lickliderian and Engelbartian way.
The public appreciation and respect for @trq212 tonight from OpenAI folks warms my heart. Great reminder that humans are gonna be alright after all. Much love y'all ❤️
Seriously, it was. Been afraid to touch it since 2003. Last night "Opus please upgrade. Do the OS too cuz um Ubuntu 8 and I have root password in the view code and no SSL kthanxbye"
Woke up to perfection.
Answering different part of this... It's really hard to intuit effort levels. Like for any given prompt/task, how to know! Doesn't feel human tractable. So before reassigning the hot key, I wonder if effort selection will be much more automated/model-selected in the near future, rendering it moot...?