I wonder if Anthropic just has better drafter models for speculative decoding an... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

SilverSlash 33 days ago | parent | context | favorite | on: Kimi K3: Open Frontier Intelligence

I wonder if Anthropic just has better drafter models for speculative decoding and more efficient prompt caching in their agent harness.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact