Cite
Notes
Only stored in your browser.
Attribution
Large Language Models can Strategically Deceive their Users when Put Under Pressure
arXiv 2023
The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
from 2 papers
Asa Cooper Stickland
researcher
Jérémy Scheurer
Lukas Berglund
Marius Hobbhahn
Max Kaufmann
Meg Tong
Owain Evans
founder
Tomasz Korbak