Jm2c I couldn't care less about this vibecode style benchmarks and I'm sick of them.
The things that I see represented here, may or may not be impressive, but sure as hell have never been the major blockers in achieving progress on complex tasks and software.
I understand you're merely reporting, thank you for that, not criticizing you, but those tests are absolutely irrelevant.
The things that I see represented here, may or may not be impressive, but sure as hell have never been the major blockers in achieving progress on complex tasks and software.
I understand you're merely reporting, thank you for that, not criticizing you, but those tests are absolutely irrelevant.