‹ BackHN Continuity

Thread

One month coding with GLM 5.3 Flash

228 points · 180 comments · ThibWeb

  1. ThibWeb · · focus · HN ↗
    It was a bit of a silly challenge, wasn’t sure how workable, learned a lot in the process about what actually drives usage / costs, and how to keep both under control
    1. sampullman · · focus · HN ↗
      Worth a comparison with DeepSeek v4.1 flash, if you've got another month to spare!
      1. nowittyusername · · focus · HN ↗
        Ill tell you from my personal use glm 5.3 flash was better then deepseek 4.1 flash, also deepseek liked to yap in his reasoning traces soo fucking much, the yapping was fast but the task was so slow to complete...
        1. sampullman · · focus · HN ↗
          I've only compared it in a few tool assisted design tasks, and deepseek performed significantly better (and faster). I haven't had them do enough coding to get a feel for that, though.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.