dlarsen5

I thought that too where the same model + harnesse would always be better but databricks found using pi actually could outperform with the same model. maybe evidence that the coupling premise may not be always true

https://www.databricks.com/blog/benchmarking-coding-agents-d...

so funny that I was migrating my agent workflow off of github issues today and while I was trying to run a regression test against a run of the old github workflow it gave timeouts related to issues being down, been getting nothing but trouble the last few weeks from having github manage the project/issues