selfsimilar
Joined 14 years ago
Joined 14 years ago
Honestly, though, the next big thing that needs to happen is proper "learning" in real-time. Allow for training (weight modulation) and queries to happen simultaneously. That's the full package.
I’m currently working on a cooperative “lights-on” solution which might be complementary.
I stopped reading after this, because this is the dumbest way to vibe code anything larger than a single-use tool.
Claude is a collaborator, and honestly a decent voice of dissent, but it will never offer that unprompted. "Make this thing" - "OK".
You need to review the code. You need to say "I want this, AND HERE IS THE LONG-TERM VISION. Now offer critique and the trade-offs for various implementations."
Or just realize that in every hand-written project you learn the contours of the problem space as you go along and if the tool is big enough you'll feel the urge to do a green-field rewrite of hand-rolled code after a few years. You get there quicker with the robot's help. This is not a new lesson.