Alexander Lerchner is a senior researcher at Google DeepMind specializing in machine learning and artificial intelligence research. He is known for his theoretical work on consciousness, subjective experience, and the philosophical foundations of artificial intelligence systems.
Lerchner's research addresses fundamental questions about the nature of consciousness and subjective experience in artificial systems. His work examines the distinction between the instantiation of conscious processes—the actual implementation of mechanisms that could generate subjective experience—and the mere simulation of consciousness, where systems exhibit behavioral characteristics consistent with consciousness without possessing genuine subjective experience 1).
This distinction forms a crucial philosophical and technical divide in contemporary AI research. Lerchner's approach emphasizes the importance of mechanistic understanding rather than behavioral criteria alone when evaluating claims about machine consciousness or subjective experience.
Lerchner authored “The Abstraction Fallacy,” a theoretical paper that challenges assumptions about the relationship between computational sophistication and consciousness. The paper argues that achieving artificial general intelligence (AGI) would not necessarily result in artificial consciousness, and that consciousness may require properties fundamentally different from those that enable advanced reasoning or goal-directed behavior 2).
The central thesis proposes that many researchers commit an abstraction fallacy by assuming that sufficiently advanced information processing automatically generates subjective experience. This assumption, according to Lerchner's analysis, lacks sufficient justification and conflates different categories of phenomena—computational capability on one hand and phenomenal consciousness on the other 3).
Lerchner's research has implications for how researchers approach AI safety, alignment, and evaluation. If consciousness and subjective experience do not necessarily follow from computational advancement, then questions about machine suffering, moral status of AI systems, and ethical obligations toward artificial minds require different analytical frameworks than conventional approaches might suggest 4).
This work contributes to a growing body of research in the philosophy of mind and AI ethics that questions anthropomorphic assumptions about machine minds and emphasizes the importance of rigorous philosophical analysis alongside technical development.
As a senior researcher at Google DeepMind, Lerchner continues to publish theoretical work examining foundational questions in AI and consciousness studies. His research represents an important voice in contemporary debates about the relationship between artificial intelligence capability and subjective experience, particularly as AI systems continue to grow in sophistication and capability.