Entropic boundary conditions towards safe artificial superintelligence

Research output: Contribution to journalArticlepeer-review


Artificial superintelligent (ASI) agents that will not cause harm to humans or other organisms are central to mitigating a growing contemporary global safety concern as artificial intelligent agents become more sophisticated. We argue that it is not necessary to resort to implementing an explicit theory of ethics, and that doing so may entail intractable difficulties and unacceptable risks. We attempt to provide some insight into the matter by defining a minimal set of boundary conditions potentially capable of decreasing the probability of conflict with synthetic intellects intended to prevent aggression towards organisms. Our argument departs from causal entropic forces as good general predictors of future action in ASI agents. We reason that maximising future freedom of action implies reducing the amount of repeated computation needed to find good solutions to a large number of problems, for which living systems are good exemplars: a safe ASI should find living organisms intrinsically valuable. We describe empirically-bounded ASI agents whose actions are constrained by the character of physical laws and their own evolutionary history as emerging from H. sapiens, conceptually and memetically, if not genetically. Plausible consequences and practical concerns for experimentation are characterised, and implications for life in the universe are discussed.

Original languageEnglish (US)
Pages (from-to)1-33
Number of pages33
JournalJournal of Experimental and Theoretical Artificial Intelligence
Issue number1
StatePublished - 2023


  • AI safety
  • artificial superintelligence
  • causal entropic forces
  • global risks
  • maximum entropy principle

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Theoretical Computer Science


Dive into the research topics of 'Entropic boundary conditions towards safe artificial superintelligence'. Together they form a unique fingerprint.

Cite this