SWE-bench Verified no longer measures frontier coding capabilities
1–10 of 209 posts
Re: SWE-bench Verified no longer measures frontier coding capabilities
#2I mean, it's fine as it's useful for many people, but where is the button for disabling it ? Or why is it enabled by default ?
"codage de pointe" sounds so weird and cringe in French.
Re: SWE-bench Verified no longer measures frontier coding capabilities
#3Re: SWE-bench Verified no longer measures frontier coding capabilities
#4This feels very much like "we are now moving the goal posts".
Re: SWE-bench Verified no longer measures frontier coding capabilities
#5Re: SWE-bench Verified no longer measures frontier coding capabilities
#6I don't understand these websites which force translation to my native language. I mean, it's fine as it's useful for many people, but where is the button for disabling it ? Or why is it enabled by default ? "codage de pointe" sounds so weird and cringe in French.
Re: SWE-bench Verified no longer measures frontier coding capabilities
#7I don't understand these websites which force translation to my native language. I mean, it's fine as it's useful for many people, but where is the button for disabling it ? Or why is it enabled by default ? "codage de pointe" sounds so weird and cringe in French.
Re: SWE-bench Verified no longer measures frontier coding capabilities
#8I don't understand these websites which force translation to my native language. I mean, it's fine as it's useful for many people, but where is the button for disabling it ? Or why is it enabled by default ? "codage de pointe" sounds so weird and cringe in French.
Does your browser request French via an Accept-Language header perhaps? What really infuriates me is when sites don’t respect that header and give you a translation based on IP location.
Re: SWE-bench Verified no longer measures frontier coding capabilities
#9Terminal Bench is the future
Re: SWE-bench Verified no longer measures frontier coding capabilities
#10This feels very much like "we are now moving the goal posts".
But this is the good kind of goalpost moving
They're saying they need to move on from it because the benchmark is flawed (without bringing in proof) and that's why they can't hit 100%.
It's not a "our models are so good that the benchmark is too easy" thing.