‹ 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. cvburgess · · focus · HN ↗
      Considering they were your top two models, how did the flash and non-flash versions compare? Did you use them for different tasks?
      1. RussianCow · · focus · HN ↗
        Not OP, but I've used both quite a bit and I think GLM 5.3 (non-flash) is a vastly better model. The flash variant is good for general workhorse agents, but it doesn't seem to reason holistically about code and over-engineers solutions to each specific problem it solves. But if you use GLM 5.3 to write a detailed plan with little to no ambiguity, GLM 5.3 Flash executes it just fine for a fraction of the price.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.