| ▲ | dakolli 7 hours ago | |
try here, I hate llms but this is crazy fast. https://chatjimmy.ai/ | ||
| ▲ | bmacho 7 hours ago | parent | next [-] | |
| ||
| ▲ | Lalabadie 7 hours ago | parent | prev | next [-] | |
The full answer pops in milliseconds, it's impressive and feels like a completely different technology just by foregoing the need to stream the output. | ||
| ▲ | machiaweliczny 5 hours ago | parent | prev | next [-] | |
We need that for this chinese 3B model that think 45s for hello world but also solves math. | ||
| ▲ | FergusArgyll 6 hours ago | parent | prev [-] | |
Because most models today generate slowish, they give the impression of someone typing on the other end. This is just <enter> -> wall of text. Wild | ||