‹ BackHN Continuity

Thread

Cache-to-Cache: Direct Semantic Communication Between LLMs (2025)

109 points · 22 comments · rochansinha

  1. djoldman · · focus · HN ↗
    Seems like fundamentally a cool idea but: KV is not context. if the KV cache gets evicted, you'd have to rerun the translation.

    Seems like it could still help but also feels like one of those things where it becomes vastly more complex and difficult to debug.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.