alt Hacker NewsOk, but why did they chose Sonnet in the first place? Couldn't they have chosen Haiku or GPT Luna or maybe even some small cheap Chinese model?
Replies
theshrike79 • today at 8:07 AM
I’m guessing accuracy. Smaller models are just THAT much more inaccurate to not make it viable.
Hamuko • today at 8:22 AM
Not sure if it would even need to be a small Chinese model. Amazon would surely have the necessary hardware and infrastructure to run a bigger Chinese model with a low per-token cost too. They probably get their Sonnet at a discounted rate too since they do the inference "locally", but I imagine the savings for not having to pay Anthropic their share would still add up.
Strands decider actually uses a small cheap/free Chinese model for its base architecture: Qwen