|
| ▲ | swalsh 5 hours ago | parent | next [-] |
| I think it's a joke at this point, but also the visual benchmark is a remarkably dense method for demonstrating how good a model is. |
| |
| ▲ | InsideOutSanta 5 hours ago | parent [-] | | Yeah, people like to poop on the pelican. But pelican quality still correlated with overall model capabilities reasonably well, and you can immediately see and interpret it. It's a running gag, but it also does have some actual value. |
|
|
| ▲ | InsideOutSanta 5 hours ago | parent | prev [-] |
| So do you have the pelican or no? |
| |
| ▲ | rvz 4 hours ago | parent [-] | | [flagged] | | |
| ▲ | tomhow 4 hours ago | parent | next [-] | | Can you please not be so sneery/grouchy? That's far worse for HN than suboptimal benchmarks. The guidelines specifically ask us to avoid being curmudgeonly. | |
| ▲ | Mashimo 43 minutes ago | parent | prev | next [-] | | What is i want to code svg files though? | |
| ▲ | InsideOutSanta 3 hours ago | parent | prev [-] | | Ok, so I looked at all of your links, but nary a pelican to be found. How am I supposed to know what all these numbers mean if there is no pelican? |
|
|