Thread

1. awfm9 · 1789986908 · focus · HN ↗

   What's the advantage of doing this, versus becoming good at context management and RAG? I always found trained knowledge unreliable, given that it is lossy by construction.

   1. truejaian · 1790091125 · focus · HN ↗

      I don't think there's much of advantage tbh. Memories in files will always outperform non-frontier model weight adjustments imo.

      1. awfm9 · 1790343941 · focus · HN ↗

         I always found the frontier AI labs' focus on trained knowledge a bit confusing. From my perspective, training creates a reasoning engine. Beyond that, models reason about data from more reliable sources. I wonder why this is not a distinction they make?

Unofficial Hacker News client; not affiliated with Y Combinator.