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. dmos62 · 1789893704 · focus · HN ↗

      I disagree. Parallelization, coordination shouldn't be model-level functionality. Further, how do you know if or when we'll get orders of magnitude increases in context sizes. Or, do you mean that the labs will just nail the perfect plug-and-play harness? That's fair, but why wait.

Unofficial Hacker News client; not affiliated with Y Combinator.