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://typesafe.ai/manifesto" rel="nofollow">https://typesafe.ai/manifesto
love that you love the manifesto! letting the first batches off the waitlist now, but we do have some early users describing their experience (<a href="https://x.com/danshipper/status/2099947471518474522" rel="nofollow">https://x.com/danshipper/status/2099947471518474522)
ramon156 · · focus · HN ↗
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://typesafe.ai/manifesto" rel="nofollow">https://typesafe.ai/manifesto
CompleteSkeptic · · focus · HN ↗
varenc · · focus · HN ↗