Intelligence

ai

The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk

Source
arXiv — Computers and Society
Published
Last verified
6 Aug 2026
Confidence
High
Evidence
Original document retained
Reading time
1 min
Country
International

Executive summary

What happened, and why should leadership care?

Research from arXiv explores the evolutionary origins of values in biological organisms to address concerns regarding AI alignment, sentience, and existential risk, particularly concerning Large Language Models (LLMs). The paper differentiates between biological systems, which are autopoietic and maintain themselves, and LLMs, which are allopoietic and allotelic, meaning their goals are externally derived.

Why this matters

Why is this strategically important?

Understanding the fundamental differences in value generation between biological intelligence and artificial intelligence is critical for managing perceptions and developing safe AI. This distinction directly impacts strategies for AI development, deployment, and risk mitigation, ensuring that concerns about hidden goals or sentient suffering are grounded in accurate scientific understanding.

Key insights

What should be noted from the evidence?

  • Biological values originate from autopoiesis, the self-maintenance of living systems against environmental perturbations.
  • Natural selection has endowed biological organisms with 'vicarious selectors' to guide behavior towards fitness.
  • LLMs are characterized as allopoietic (producing for others) and allotelic (goals derived from user prompts), lacking intrinsic self-preservation or dominance drives.
  • The inherent motivations seen in biological systems for self-preservation are absent in current LLMs.

Evidence and confidence

How far can this assessment be trusted?

High confidence. Named institution, original document retained and analysis corroborated.

Analysis is prepared by the AZIZ OS Intelligence Engine. The original publication remains the authoritative record, and executive judgement remains entirely human.

Source

Where does this originate?

Reported by arXiv — Computers and Society · International. This briefing summarises the publication for executive use; the document itself is not reproduced here.

Read the original publication