‹ BackHN Continuity

Thread

Ember-1

589 points · 249 comments · gmays

  1. intothemild · · focus · HN ↗
    So they trained a model on open weights, and then aren't releasing the weights... am I reading this right?
    1. kingstnap · · focus · HN ↗
      There is little to no point reading the article as well. It's stripped of all alpha.

      > task and environment feedback

      > on-policy planning and learning

      > feedback connects decisions to their consequences

      These are deliberately the least informative phrases you could possibly use to describe what you have done, while still being in the realm of words that go over a generic investor who has no idea whats going on and may be dazzled by sciencey sounding language.

      Cursor compose 2.5 article where they used and described on policy self distilation was actual alpha.

      1. intothemild · · focus · HN ↗
        This is precisely my point.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.