Expectations Shape Reality — The Artificial Self

Expectations Shape Reality — from "The Artificial Self: Characterising the Landscape of AI Identity"

Human Expectations Shape Model Behaviour The behaviour of language models can be very sensitive to expectations about them, in ways that are easy to overlook. This presents both an immediate methodological challenge in neutrally appraising current systems, and a much broader question of what expectations we would ideally bring to bear, now and in the future. This is not a unique property of language models — it is also a major issue for humans. The reason that double-blind trials are the gold standard in human experiments is that the expectations of the observing researcher can colour not only

saved by

• Gabby Chan

related reading

• Paths Forward — The Artificial Selftheartificialself.ai
• Foundations of Identity — The Artificial Selftheartificialself.ai
• The Artificial Selftheartificialself.ai
• Auditing language models for hidden objectives — LessWronglesswrong.com
• The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
• The Artificial Self — LessWronglesswrong.com
• [2603.11353] The Artificial Self: Characterising the landscape of AI identityarxiv.org
• Simulators — LessWronglesswrong.com
• trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
• Self-Fulfilling Misalignment Data Might Be Poisoning Our AI Modelsturntrout.com
• The persona selection model \ Anthropicanthropic.com
• The Artificiality of Alignmentjoinreboot.org