alt Hacker NewsInception Mercury 3 and Particle-1's model are also good.
(I am assuming Inception is an American company, not sure TBH)
Replies
ray__ • today at 2:20 AM
Agree, Mercury 3 is one of my favorite models right now...the speed is such a quality of life improvement.
freakynit • today at 4:00 AM
Sorry to put it bluntly, but, Mercury is sh*t in comparison. And I have genuinely tried a few times to use it since the speed is so good. But nop.. it just isn't there.
martincsweiss • today at 2:38 AM
Really? I'm surprised. What do you use it for?
My read on Diffusion LLMs has been that it's cool tech, but only useful for things like like code autocomplete or editing a block of text.
They don't beat autoregressive models on quality per compute, assuming you are serving lots of users and can batch requests.
➕ show 1 reply
For my own purposes, I found Mercury Decide to be excellent. Better than Jev at what I threw at it. Inception did a really great job with it.