|
|
|
|
|
by collingreen
409 days ago
|
|
I love your premise here. I think visual programming has such untapped potential even though it has been tried and tried and tried so I hope you crack the code a bit (lol). I think you're exactly right on the idea of "I just diagrammed all the control flow why can't I just push run". It's kind of crazy to introduce a point of failure (and a menial translation step) by writing code to match the diagram. Another huge benefit that I learned when reading about drakon (obvious in retrospect) is that good visual programming makes the software development process more accessible to other smart people involved instead of locking it away behind computer jargon and tools (the drakon example was rocket scientists able to now work on, review, and validate the logic and control flow instead of having to just hope it ended up right). I hate that I'm saying this but this would actually make me feel a lot better about the vibe coding going on right now. If the control flow was right, hand crafted, and easy to review I'd feel a lot better about throwing the implementation details of many individual nodes over the wall to the ai without worrying about the house falling down. |
|
Lowering the barrier of collaboration is indeed a major goal for us. In the DRAKON analogy, Flowcode might help technical product managers collaborate with developers on LLM-heavy logic.
Re: vibe-coding - that matches our vision 100%. Let AI build the nodes while a human (even if heavily AI-assisted) oversees