tuyiown
Joined 11 years ago
Joined 11 years ago
The most ridiculous thing is that idealistic open-source maintainers are still doing it, while this is being an established status quo for at least 30 years. Or maybe they have their incentive, and, while I don't find it palatable too, large corporations understands that. What's _your_ incentive in having such strong opinions about that ?
If can put properly engineered intent in the prompt that is verifiable, it works wonders. Anything that can defaults to the llm doing its way, you're right, it just can't converge to good, not with proper constraints.
This can be a result of unexpected and costly if not worse, surprises.
Pin pointing the issue is way more than valuable than code. If you wrote a fix, you have analyzed the bug. The value is there, not in the fix. Sharing your fine analysis is the maximized contribution. Code is an optional bonus at most.
Nobody talked about anything out of neurons. The question is still open.
git push . <branch1>:<branch2>
git pull . <branch2>:<branch1>The only way to avoid getting furious about this is to deeply understand that you can't require people to be properly self-aware, especially because many many people that checks the expert boxes are very incompetent or inadequate, so they when the come up with their half bake ideas, they delegate the other to deliver contrarian proofs. It's exhausting.