You must log in or register to comment.
Finally, an LLM benchmark that can’t be faked
I’m pretty sure this was Microsoft’s versioning logic for the 90s and 2000s.
Ok! Time to relax. Sashi is a shitposter.
Wait, we are taking a microblog shitposting community’s content seriously?
Can’t wait for Elon to force grok to release 2099
thatsthejoke.tensor
Wow, first time I’ve seen a completely useless graph
Really? You’re lucky.Their lucky what?
Thanks autocorrect must have decided that ‘youre lucky’ is the start of a Madonna lyric 😂
Theyre lucky day
you just lack the super intelligence needed to fully understand it.
From the Line Goes Up school of thought.
This is a perfect example of the intelligence of those who use AI. They have become so used to not having to think or work before reacting.
Grok 86.47 for the win!
Quickly followed by grok 88.14,last major version ever, all following versions being just 88.14.x.
Sounds reliable. There’s a name for claims like that https://github.com/ajnart/trustmebrobenchmarks.com
