‹ BackHN Continuity

Thread

Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

415 points · 114 comments · moonikakiss

  1. dev_l1x_be · · focus · HN ↗
    I am not sure about GPT-5.6. It usually 10x more verbose for no apparent reason than GPT-5.5. Maybe it is only me.
    1. jr3592 · · focus · HN ↗
      Have you tried Claude? 5.6 feels less verbose, and less messy to me.
      1. dev_l1x_be · · focus · HN ↗
        Yeah Opus 4.8 / GPT 5.5 what I use. Fable is okish, the coding experience is a bit weird with it.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.