Why is this the case? Are there any architectures that don't rely on feeding the... | Hacker News

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

brcmthrowaway 34 days ago | parent | context | favorite | on: DeepSeek 4 Flash local inference engine for Metal

Why is this the case?

Are there any architectures that don't rely on feeding the entire history back into the chat?

Recurrent LLMs?

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