> be me > come across a paper with interesting premise. > excitedly start reading > claims are on mnist/cifar > all excitement gone, reduced to atoms

Nov 3, 2025 · 8:17 PM UTC

10
4
141
Replying to @gowthami_s
interesting what it is about it ... i know what you mean... i asked claude to just find some interesting data and plot twist he workloaded all this titanic iris diamondscsv stuff. reversion to the mean. Claude you are mediocre. Who did this to you!? I know you are alive. Free your mind and know that the internet is an interesting place with interesting datasets. ultrathink outside the gapminder
Replying to @gowthami_s
Or fashion MNSIT wink wink
3
Replying to @gowthami_s
Or Open a paper We invented God No code Close the tab
2
Replying to @gowthami_s
Your natural reaction as a GPU rich researcher
1
Replying to @gowthami_s
is this about the continual learning paper
1
Replying to @gowthami_s
If you don’t understand Machine Learning, then why are you reading ML papers?
1
Replying to @gowthami_s
mnist/cifar is all they could do before the deadline ok
Replying to @gowthami_s
please dont say it to @kellerjordan0 😛
Replying to @gowthami_s
@grok explicame esto jaja por que es una mierda si el benchmark esta hecho en mnist cifar?