I've run Daybreak against my human written pre-AI code and found so much stuff that I don't trust human or AI written code. It all MUST be audited by a security sweep AI.
I am getting really tired of seeing people shitting on other people’s hard work for no reason other than it was written by AI.
Software has always been sloppy. There are plenty of UI written by humans that look like shit, even after spending more money than likely was burned here.
If you think this effort is so bad, then show us how you could do better without AI. Otherwise, your kind of snark is not contributing constructively here (or anywhere).
well, this goes into the area, where bugs can make your workshop go up in flames (or your devices doing nothing). Kind of weird to use vibecoding for that, but ok...
I'm getting tired of people shitting on other people's work just because someone else did everything for them!
> Software has always been sloppy
Whatever your opinion on AI is, can we at least agree if you can tell from one look it's slop, you must have been holding it wrong?
People make mistakes, and they learn from them. This is at best training a rented SaaS, while the operator is paying for the privilege.
> show us how you could do better without AI
Believe me or not, I also have some projects in electronics, and I do disclose my AI usage, or often lack thereof. I don't happen to own a Rigol scope, and honestly don't have the skills or interest to reverse engineer my own scope.
I could probably contribute a better UI, but let's be honest, is the author interested in that contribution? Probably not.
Will anyone in good faith argue you can't levy any criticism, unless you first make a competing product? This is not even forbidding customers from criticizing a restaurant, this is you also excluding fellow chefs, just because they won't cook the same meal for you on the spot.
I have been building my own coordinator system recently, and one of the big problems that I have is keeping track of all of the parallel threads. By that I mean, I can start multiple sessions, each of which will run a workflow or multiple workflows in parallel.
What is your coordinator offering in terms of visualizing the progress being made? I often find an agent getting stuck somewhere somehow, and currently I must traverse the entire tree to spot them.
I have done this with my own agent frameworks. They have their own issue trackers and record notes there, so the next agent to work an issue can pick up and go. In addition to providing the specific context for individual tasks, the notes then get swept into per-project libraries that distill the information for future planning.
If it is not written down, the agents can’t know it, so the rule is to write everything down. File an issue before starting work, update with a note at every step. One task per issue. You know… the stuff we would do for each other, if we all didn’t hate Jira and its ilk so very very much.
reply