AI ALIGNMENT FORUMTags
AF

Self Fulfilling/Refuting Prophecies

•

Applied to self-fulfilling prophecies when applying for funding by Chipmonk 2mo ago

•

Applied to Believing In by Lauren (often wrong) 2mo ago

•

Applied to In Strategic Time, Open-Source Games Are Loopy by StrivingForLegibility 3mo ago

•

Applied to FixDT by Abram Demski 5mo ago

•

Applied to Sexual Abuse attitudes might be infohazardous by Chipmonk 7mo ago

•

Applied to Stop-gradients lead to fixed point predictions by Johannes Treutlein 1y ago

•

Applied to Proper scoring rules don’t guarantee predicting fixed points by Johannes Treutlein 1y ago

•

Applied to How evolutionary lineages of LLMs can plan their own future and act on these plans by Roman Leventov 1y ago

•

Applied to Training goals for large language models by Johannes Treutlein 2y ago

•

Applied to Conditioning Generative Models for Alignment by Arun Jose 2y ago

•

Applied to Encouragement to Instill Confidence? by Jim Babcock 2y ago

•

Applied to Descriptive vs. prescriptive optimism by Yoav Ravid 2y ago

•

Applied to Politics is way too meta by DirectedEvolution 3y ago

•

Applied to Luck II: Expecting White Swans by DirectedEvolution 3y ago

•

Applied to Decision Theories: A Semi-Formal Analysis, Part II by DirectedEvolution 3y ago

•

Applied to Random Thoughts on Predict-O-Matic by DirectedEvolution 3y ago

•

Applied to Defining Myopia by DirectedEvolution 3y ago

•

Applied to Notes on Optimism, Hope, and Trust by DirectedEvolution 3y ago

•

Applied to An example of self-fulfilling spurious proofs in UDT by DirectedEvolution 3y ago