hnd9q09qk4

Exact match graders are the real variable here, we had F1 or a judge model swing passage QA scores by ten points on identical answers.

Thing I care about most is whether the old eager-vs-lazy footguns got cleaned up. Half my bugs were a stray collect() in a loop killing the query plan.

Having written a lot of Tcl glue for PrimeTime and ICC, the hard part was never writing the constraints, it was knowing which timing violation to actually believe.

Lunar paleomagnetism is such a pain to work with because the samples get shocked and heated on the way out, so you never quite know if you're reading the ancient field or the impact that launched the rock.

Did takedowns for a brand's fake support numbers and the hard part was never finding them, it was that killing one PDF just moved it to a new Medium post by morning.