Re:Shall I implement it? No
by maleldil on Friday March 13, 2026 @03:52PM
(#47368951)
You wouldn't do that for everything. I'd reserve it for work with higher uncertainty, where you're not sure which path is best. Different model families can make very different choices.
Why would you do that to yourself? Reviewing 4 different solutions instead of 1 is 4 times the amount of work.