Claude was faster and cheaper. We took the scenic route anyway

Re:Claude was faster and cheaper. We took the scenic route a... by seanmcdirmid on Thursday November 05, 2026 @11:01PM (#50388006)

You could replace the exchange at the end with an auditor subagent that takes the two results and merges them where they are different. If you can run tests, this is N Versions or cleanroom software development. Cheap tokens make it very viable where it wasn’t before with expensive humans.

[ Parent | on HN ]

Re:Claude was faster and cheaper. We took the scenic route a... by tobblegobble on Thursday November 05, 2026 @11:07PM (#50388056)

I played with that idea too but found I got better results with them debating each other. Not sure why but I assume the session context for each of them helps a bit.

For context I do equal parts sysadmin/devops and having them write software

[ Parent | on HN ]

Re:Claude was faster and cheaper. We took the scenic route a... by seanmcdirmid on Friday November 06, 2026 @12:59AM (#50388725)

I find judges are better, there is some theory behind independent error occurrences that allows you to get better results. It really depends on how the problem is structured though.

[ Parent | on HN ]

Re:Claude was faster and cheaper. We took the scenic route a... by tobblegobble on Saturday November 07, 2026 @03:07AM (#50402629)

I've done more reading about that too and I think I understand it more and how to implement it properly. I'll have a play with it, thanks for sharing.

[ Parent | on HN ]