Thread

1. hehimself · 1790100160 · focus · HN ↗

   Love the price reductions across major players

   1. madduci · 1790100317 · focus · HN ↗

      Because Qwen4 has been announced!

      1. eloisant · 1790102138 · focus · HN ↗

         And GLM 5.3 works great

         1. system2 · 1790115017 · focus · HN ↗

            Except for the censorship. We use it for massive data crunching, and roughly 5-8% (depending on the day) gets censored and doesn't get a response. We switched to Mimo 2.6, which is relatively better. For censored stuff, we use Sonnet and OpenAI Nano models.

            Also Mimo 2.6 is roughly 30% cheaper. Without batch.

            1. Havoc · 1790124597 · focus · HN ↗

               What sort of content is it censoring? Politics I assume?

               1. system2 · 1790130868 · focus · HN ↗

                  News mostly. Anything China-related gets censored without hesitation. Some random stuff got censored too. It is borderline unusable, to be honest, unless only numbers are crunched.

                  1. Havoc · 1790151674 · focus · HN ↗

                     Interesting. Was planning to use it for a news related thing too. I guess one can throw Jev at it first to ask whether it relates to China and then decide?

                     Or use the failure to get a response like you say

                     1. system2 · 1790221493 · focus · HN ↗

                        We are using it with OpenAI Luna. We send any failed query to Luna, and the operation is complete.

Unofficial Hacker News client; not affiliated with Y Combinator.