Instant AI Response (chatjimmy.ai)

What model and hardware powers this?

Is this a Google T5 based model?

This is a demo of Taalas inference ASIC hardware. Prior discussion @ https://news.ycombinator.com/item?id=47086181

- https://news.ycombinator.com/item?id=47086181

- https://taalas.com/the-path-to-ubiquitous-ai/

- https://www.nextplatform.com/2026/02/19/taalas-etches-ai-mod...

If this is possible, why not all online AI engines work like this?

I love seeing optimised SLM inference. Is there a current use-case for this? Edge CNNs make sense to me but not edge SLMs (yet).

imagine a model like opus 4.6 at that speed, that would be insane

Impressive, but this particular underlying LLM is objectively weak. I'd like to see it done with a larger and newer better model.