@MatthewBerman Try this. Don't blink.
https://chatjimmy.ai/
Matthew Berman@MatthewBerman
I wish LLMs ran 1000x faster.
Do you fully understand the economic unlock of that?
12:22 PM · Jun 23, 2026 · 1.3K Views
Nick Dobos launches chatjimmy.ai web interface to demonstrate near-instant LLM response delivery
The rapid generation prompted questions about the underlying serving stack.
515151.8K
Sentiment
Sentiment building, check back later.
Cluster Engagement
Digg Deeper
No Digg Deeper questions have been answered for this story yet.
Related links
Posts from X
Most Activity
Most Activity
VIEWS677LIKES5REPLIES3
Matthew Berman@MatthewBerman
@NickADobos wtf....how?
Nick Dobos@NickADobos
@MatthewBerman Try this. Don't blink.
https://chatjimmy.ai/
2hViews 677Likes 5Bookmarks 0
Nick Dobos@NickADobos
1. It’s a small model. Nowhere near the big leading ones.
2. They built custom chips and trained the model to work with it. They explain it somewhere on the website. I believe they are working on a v2 now with a bigger smarter model.
I believe other companies including OpenAI are working on similar projects with custom chips.
2hViews 84Likes 2
Nick Dobos@NickADobos
@MatthewBerman Also IIRC they actually burn it into the chip. So once you train the model and build the chips you can’t upgrade it or swap to a new model. You would need to build brand new chips.
So it’s a very different technique vs a chip that can run any type of inference
2hViews 77Likes 1
The Gadgets Fan@thegadgetsfan
@MatthewBerman @NickADobos LLM burned into silicon.
2hViews 11Likes 1