Search papers, labs, and topics across Lattice.
This paper explores the evolutionary origins of values in biological organisms to address concerns about the potential hidden goals of AI systems, particularly Large Language Models (LLMs). It argues that while biological entities possess intrinsic motivations shaped by natural selection, LLMs are fundamentally different as they lack autonomous drives and instead generate outputs based on user prompts. The study concludes that the primary alignment challenge is not rogue AI agency but ensuring LLMs effectively apply the ethical values they learn from human-generated text.
LLMs lack the intrinsic motivations for self-preservation or dominance, fundamentally altering the landscape of AI alignment concerns.
AI systems based on Large Language Models (LLMs) have prompted fears that they may harbor hidden goals, seek to dominate or eliminate humanity, or even suffer as sentient beings. We address these concerns by tracing the evolutionary origin of value in biological organisms. Values emerge from autopoiesis: living systems must actively maintain themselves against perturbation and dissipation. Natural selection has equipped them with hierarchies of"vicarious selectors"that guide their behavior toward fitness. LLMs, by contrast, are allopoietic and allotelic: they produce outputs for others, and their goals derive from user prompts rather than an autonomous drive. They lack the intrinsic motivation for self-preservation, dominance, or resource competition that underlies existential-risk scenarios, and the embodied vulnerability required for feeling or suffering. Still, because LLMs learn statistical patterns from human-generated text, they implicitly absorb human values as well as knowledge, allowing them to focus on what is relevant. That is why the"orthogonality thesis"separating intelligence from values does not apply to them. Such separation would in fact expose any intelligence to the frame problem: the combinatorial explosion of the search space that makes any realistic utility function physically uncomputable. That also precludes the convergence of instrumental values thesis. We conclude that the real alignment challenge lies not in preventing rogue AI agency, but in ensuring LLMs intelligently apply learned ethical values.
