Thread

1. simianwords · 1789889196 · focus · HN ↗

   Bitter lesson means all these tricks will not be needed in a year or two. Either labs will abstract it in harness or models will become good enough that it can do it by itself

   1. normie3000 · 1789889837 · focus · HN ↗

      So we should just ignore?

      1. dannyw · 1789891153 · focus · HN ↗

         If you’re using models today, it’s worth it.

         Yes it’ll eventually get built into the harness/model/interface; just like how “work it out step by step” became thinking, but if you have work to do today, it can be worth trying to improve it.

Unofficial Hacker News client; not affiliated with Y Combinator.