Whole Brain Emulation as an Anchor for AI Welfare - Benjamin Sturgeon website

Epistemic status: Fairly confident in the framework, uncertain about object-level claims. Keen to receive pushback on the thought experiments.

28 December 2025 Whole Brain Emulation as an Anchor for AI Welfare Originally posted on LessWrong Epistemic status: Fairly confident in the framework, uncertain about object-level claims. Keen to receive pushback on the thought experiments. TL;DR: I argue that Whole Brain Emulations (WBEs) would clearly have moral patienthood, and that the relevant features are computational, not biological. Recent MI work shows LLMs have emotional representations with geometric structure matching human affect. This doesn't prove LLMs deserve moral consideration, but it establishes a necessary condition, and w

saved by

• Sudarsh K

related reading

• Whole Brain Emulation: No Progress on C. elegans After 10 Years — LessWronglesswrong.com
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Whole Brain Emulation: No Progress on C. elegans After 10 Years — LessWronglesswrong.com
• A Workaphile’s Apologymoalquraishi.wordpress.com
• Simulators — LessWronglesswrong.com
• We should take AI welfare seriously - by Robert Longexperiencemachines.substack.com
• Experts Who Say That AI Welfare is a Serious Near-term Possibilityeleosai.org
• Emotion concepts and their function in a large language model \ Anthropicanthropic.com
• 2311.08576arxiv.org
• The Machines Lack Honour — LessWronglesswrong.com
• Artificial intelligence by mimicking natural intelligencesubstack.com
• [2605.21739] AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligencearxiv.org