epic9x 2 days ago

This thing is crazy fast.

1
smeeth 2 days ago

They have a deal with Cerebras for inference.

https://www.cerebras.ai/blog/mistral-le-chat

swah 2 days ago

For me this is more important than quality. I love fast responses, feels more futuristic.

pxc 1 day ago

What are you using LLMs for?

swah 8 hours ago

Mostly "How is $term in English", what is $thing, review this message for clarity, clean up this data, parse this screenshot, and coding.

pxc 3 hours ago

I see! So for these, you tend to find the accuracy "good enough" on the faster-but-less-accurate models.

I generally find the same thing for simple definitions/translations and other "chat" tasks. I'm a little bit surprised that you also find it so for coding, but otherwise I think I get it.