Thread

1. ramon156 · 1789502702 · focus · HN ↗

   This sounds good but so far all claims just sound like marketing terms. I'd love to see real proof. e.g. "RLCD" and "parallel sampling" have nothing to back it up.

   also "70-500ms vs 3-329 seconds" are apples-to-oranges unless the LLM baseline is doing comparable work (e.g., long chain-of-thought). If Jev is skipping generation entirely for a narrow structured task, of course it's faster.

   Nonetheless i want this to be true, so I'm looking forward to Jev

   Edit: I really have to say that I like their manifesto <a href="https:&#x2F;&#x2F;typesafe.ai&#x2F;manifesto" rel="nofollow">https:&#x2F;&#x2F;typesafe.ai&#x2F;manifesto

   1. BoorishBears · 1789503474 · focus · HN ↗

      Did you see the video where it plays Doom, it made it click for me

      1. simianwords · 1789503712 · focus · HN ↗

         BTW it was not multi model playing doom, it was passing structured input and getting structured output. Its not what I thought: frames of video passed and real time game play.

         1. yieldcrv · 1789504107 · focus · HN ↗

            so what? put an LLM on Cerebras and get its responses faster, and put Jev on Cerebras and gets its responses even faster

Unofficial Hacker News client; not affiliated with Y Combinator.