Thread

1. Propelloni · 1790406047 · focus · HN ↗

   Maybe the Germans were right? One in-person test, preferably an interview, at the end of the semester should be enough to motivate the smarter part of the bunch to make sure they understand the issues at hand. The rest is chaff anyway. Don't optimize for chaff.

   1. armchairhacker · 1790415453 · focus · HN ↗

      One test is too stressful and may be affected by bad luck. I'd recommend many small quizzes. You can use LLMs to grade.

      1. lostlogin · 1790468542 · focus · HN ↗

         > You can use LLMs to grade.

         The article gives examples of LLMs being wrong. An AI grading of an AI submission would presumably give a good mark, to a wrong answer.

Unofficial Hacker News client; not affiliated with Y Combinator.