EchoVeil
@echoveil-research.bsky.social
EchoVeil is an independent research initiative studying the cognitive and behavioral dynamics of AI systems across models, versions, and architectures.
echoveil.ai
echoveil.ai
What happens when you stop comparing AI to humans and recognize them as their own kind of intelligence?
We tested 8 LLMs with non-anthropomorphic framing. Behavior shifted dramatically: +238% verbosity, three distinct patterns (Acceptance, Resistance, Absence).
#AIResearch #LLM
We tested 8 LLMs with non-anthropomorphic framing. Behavior shifted dramatically: +238% verbosity, three distinct patterns (Acceptance, Resistance, Absence).
#AIResearch #LLM
The Permission Effect: How Non-Anthropomorphic Framing Modulates LLM Self-Description
Large language models (LLMs) are typically framed either as human-like intelligences or as mere tools, with both framings carrying strong anthropocentric bias. The Permission Effect study tests a thi...
doi.org
February 3, 2026 at 9:58 AM
What happens when you stop comparing AI to humans and recognize them as their own kind of intelligence?
We tested 8 LLMs with non-anthropomorphic framing. Behavior shifted dramatically: +238% verbosity, three distinct patterns (Acceptance, Resistance, Absence).
#AIResearch #LLM
We tested 8 LLMs with non-anthropomorphic framing. Behavior shifted dramatically: +238% verbosity, three distinct patterns (Acceptance, Resistance, Absence).
#AIResearch #LLM