twerkmeister
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @03:07PM (#48951104)
The data set quality and much of the methodology is just as abysmal as the writeup... as pointed out in my second post: https://www.kaggle.com/competitions/kaggle-measuring-agi/dis...
So it must have been the "results" that moved the needle :D
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @11:46AM (#48948752)
I updated my post title to reflect the original title and send a mail to the mods to restore the original title. Lets see. I was not aware of the editorialized title rule otherwise I had updated my post before linking it here.
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @10:55AM (#48948134)
What do you think my two long posts in the discussion forum of kaggle are? I am the author and the evidence I present very much justified the original title.
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @10:51AM (#48948088)
They also host the arc prize challenge with prices up to 850k https://www.kaggle.com/competitions/arc-prize-2026-arc-agi-3...
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @10:45AM (#48948019)
I am the author of the linked article, so you say my opinion should be allowed in the title?
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @10:39AM (#48947944)
They also removed the fact it was a competition hosted by a prestigious AI lab
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @10:18AM (#48947692)
Please note this Post was just renamed without my involvement from:
Blatant AI slop just won a 25K USD Deepmind Kaggle Grand Prize
into
"Evidence of inconsistencies in evaluate process and selection of winners"
Re:Blatant AI slop just won a 25k USD DeepMind Kaggle Grand Prize
on Friday July 17, 2026 @09:08AM (#48946967)
That's fair and your good right. However know that my frustrations stems from spending two and a half days feeling like in the story of the emperors new clothes digging into this shit that was made king by a number of employees of one of the most prestigious AI labs.
Show HN: Tokenflood – simulate arbitrary loads on instruction-tuned LLMs
https://github.com/twerkmeister/tokenflood
Hi everyone, I just released an open source load testing tool for LLMs:https://github.com/twerkmeister/tokenflood=== What is it and what problems does it solve? ===Tokenflood is a load testing tool for instruction-tuned LLMs hat can simulate arbitrary LLM loads in terms of prompt, prefix, and output lengths and requests per second. Instead of first collecting prompt data for different load...