✳flâneur — a map of the web's best reading
Expectations Shape Reality — The Artificial Self
theartificialself.ai · 1,674 words · saved by 1 readers
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
Explore this link on the map →related reading
- The Artificial Self — LessWronglesswrong.com
- The Artificial Selftheartificialself.ai
- The Persona Selection Model: Why AI Assistants might Behave like Humansalignment.anthropic.com
- trees are harlequins, words are harlequins - the voidnostalgebraist.tumblr.com
- llm assistant personas seem increasingly incoherent (some subjective observations) — LessWronglesswrong.com
- Role-playing vs Self-modelling — LessWronglesswrong.com
- [2603.11353] The Artificial Self: Characterising the landscape of AI identityarxiv.org
- The persona selection model — LessWronglesswrong.com
- The persona selection model \ Anthropicanthropic.com
- Paths Forward — The Artificial Selftheartificialself.ai
- A case for LLMs as Self-predictors — LessWronglesswrong.com
- Discovering Language Model Behaviors with Model-Written Evaluations — LessWronglesswrong.com