alt Hacker News> My experience with Anthropic is that despite using Opus 4.6 and 4.7, most of the time the performance is matching low B parameter Qwen.
Is this just the next level of the "they're serving quantized models!" theory?
> My experience with Anthropic is that despite using Opus 4.6 and 4.7, most of the time the performance is matching low B parameter Qwen.
Is this just the next level of the "they're serving quantized models!" theory?
Not a theory buy lived experience. You never know when you get the nerfed session.