News for hackers. Stuff that matters.
Re:Benchmarking Opus 5 on SlopCodeBench by anentropic on Tuesday July 28, 2026 @07:41AM (#49082373)
So far my 'solution' to this has been periodically run a separate round of whole-codebase code review (preferably Fable) and then rounds of refactoring off the results of that
Re:Benchmarking Opus 5 on SlopCodeBench by thatfunkymunki on Tuesday July 28, 2026 @09:25AM (#49083510)
yes, this has been my preferred approach as well. Too much risk of very deep local maxima otherwise.