Remix.run Logo
formerly_proven 5 hours ago

Surely the system prompt is cached across accounts?

sigmoid10 4 hours ago | parent | next [-]

You can cache K and V matrices, but for such huge matrices you'll still pay a ton of compute to calculate attention in the end even if the user just adds a five word question.

cfcf14 5 hours ago | parent | prev [-]

I would assume so too, so the costs would not be so substantial to Anthropic.