‹ BackHN Continuity

Thread

Jev in 25 Lines of Python

691 points · 212 comments · bashbjorn

  1. brap · · focus · HN ↗
    What I don’t understand is, why would you not want “reasoning” in a classifier?

    Speed and cost are obvious reasons, but isn’t this a tradeoff?

    1. ph1l337 · · focus · HN ↗
      not sure if true, but if you look at laya they use BERT type models. If jev is also using a BERT-type model it is autoregressive and therefore can't reason in the way that GPT-type models can. However, you get the advantage of being able to attend in both directions.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.