‹ BackHN Continuity

Thread

LLM Classification Is Feature Engineering

116 points · 25 comments · minsufficient

  1. wodenokoto · · focus · HN ↗
    Shouldn’t we expect the LLM model in this case to already be trained on the test and train dataset?
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.