Thread

1. Gareth321 · 1790064431 · focus · HN ↗

   OpenAI usage limits have been severely cut, and intelligence appears to be markedly declining, so I'm going to start trying these Chinese models seriously now. I don't mind if it takes longer. I just need the intelligence to predictably work the same way from day to day.

   1. unsupp0rted · 1790065693 · focus · HN ↗

      Same- I pay $200/mo for Codex but whereas I used to get a week's work out of a weekly limit, now I get roughly 1~2 days.

      I've stopped using Astra entirely and remain on Sol orchestrating Luna Xhigh, but it's still not nearly a week's usage for a week's allotment.

      And even then, whenever a new model is about to come out, it feels like the model I'm using is being dumbed down substantially.

      I have no evidence for this and can have no evidence for this, but I can vote with my wallet regardless.

      1. jmaker · 1790090908 · focus · HN ↗

         For me Sol is less efficient than Astra - Sol makes many avoidable mistakes and has issues with context compaction - sometimes it goes haywire after a couple compactions.

         Agreed on the “being dumbed down” observation. It appears they’re most powerful at release time and then are gradually “optimized” so every new model feels more powerful. But there’s no evidence on routing to a deployment with other weights. It would be plausible to do so though at least at peak times.

         1. jmaker · 1790092907 · focus · HN ↗

            What really is fun is when the opposite of the public outcry about purported distillation happens - when Astra in Codex suddenly responds in Chinese. Now that is fun. Wonder what it’s routing to.

Unofficial Hacker News client; not affiliated with Y Combinator.