Once you begin to see the “model” as only part of the stack, you begin to realize that you can draw the line of the system to include the user as well.
That’s when the future really starts hitting you.
Aha! A true cybernetics enthusiast. I didn't say that because I didn't want to scare people off ;)
That's next-year's problem.
yeah this clicked for me when i stopped obsessing over which model to use and focused on how i structure the context and feedback loops around it. for my project the same model went from "barely usable" to "legitimately helpful" just by changing how i fed it context and how i validated its output.
the user inclusion part is real too. the best results i get aren't from fully autonomous agents, they're from tight human-in-the-loop cycles where i'm steering in real time. the model does the heavy lifting, i do the architectural decisions and error correction. feels more like pair programming than automation.