Situational Awareness

non-profit

AI & ML interests

None defined yet.

Recent Activity

nikebless authored a paper about 1 year ago

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

nikebless authored a paper about 1 year ago

Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure

tomekkorbak authored a paper over 1 year ago

Inverse Scaling: When Bigger Isn't Better

View all activity

owain-sita's activity

nikebless

authored 2 papers about 1 year ago

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

Paper • 2309.12288 • Published Sep 21, 2023 • 3

Technical Report: Large Language Models can Strategically Deceive their Users when Put Under Pressure

Paper • 2311.07590 • Published Nov 9, 2023 • 16

tomekkorbak

authored a paper over 1 year ago

Inverse Scaling: When Bigger Isn't Better

Paper • 2306.09479 • Published Jun 15, 2023 • 9