‹ BackHN Continuity

Thread

Mercury 2.5 LLM hits 770 tokens per second

151 points · 92 comments · Retro_Dev

  1. jjcm · · focus · HN ↗
    I&#x27;m still sad that we haven&#x27;t seen a new Taalas style chip a la <a href="https:&#x2F;&#x2F;chatjimmy.ai&#x2F;" rel="nofollow">https:&#x2F;&#x2F;chatjimmy.ai&#x2F;. Smaller models are good enough now to make that insane burst of tokens so useful.
    1. winwang · · focus · HN ↗
      Pretty sure context is in SRAM, and then you have that as a blocker for tasks.
      1. electroglyph · · focus · HN ↗
        way less of a blocker these days due to sparse attention...
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.