10 comments

[ 2.1 ms ] story [ 32.1 ms ] thread
Super cool! really excited to try this. Although I remain skeptical if GOOD science papers can be generated
OP here: We have data source powered research papers in the making, that reports on experiments executed with codegen - really hopeful that the papers can be informative at a minimum.

It's clear that superhuman citation depth & breadth is already imminent. Hopefully we can push hallucinations to near-zero with the next generation of models.

that's great, yeah! what is the data source for the papers?
Feels like we’re going to see academia being flooded with crap
or perhaps, free scientists to focus on genuine insight, ending publish or perish forever
how do you check for hallucinations?
For now, the researcher using our tool needs to check.