# Biospheric AI

arXiv: https://arxiv.org/abs/2401.17805 · HTML: https://mlsanity.com/paper/2401.17805/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 59 references that are in the map.
- First posted on arXiv 31 Jan 2024.

## Builds on (most cited first, 16 of 16)

- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [A General Language Assistant as a Laboratory for Alignment](https://mlsanity.com/paper/2112.00861/) (2021)
- [Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2307.15217/) (2023)
- [Green AI](https://mlsanity.com/paper/1907.10597/) (2019)
- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Is Power-Seeking AI an Existential Risk?](https://mlsanity.com/paper/2206.13353/) (2022)
- [A Systematic Review of Green AI](https://mlsanity.com/paper/2301.11047/) (2023)
- [AVES: Animal Vocalization Encoder based on Self-Supervision](https://mlsanity.com/paper/2210.14493/) (2022)
- [BEANS: The Benchmark of Animal Sounds](https://mlsanity.com/paper/2210.12300/) (2022)
- [Speciesist bias in AI -- How AI applications perpetuate discrimination and unfair outcomes against animals](https://mlsanity.com/paper/2202.10848/) (2022)
- [Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whales](https://mlsanity.com/paper/2104.08614/) (2021)
- [Modeling Animal Vocalizations through Synthesizers](https://mlsanity.com/paper/2210.10857/) (2022)
- [Hybrid Life: Integrating Biological, Artificial, and Cognitive Systems](https://mlsanity.com/paper/2212.00285/) (2022)
- [A benchmark for computational analysis of animal behavior, using animal-borne tags](https://mlsanity.com/paper/2305.10740/) (2023)

## Built on by (most cited first, 1 of 1)

- [The Many-Body Problem of the Data Centre](https://mlsanity.com/paper/2606.30206/) (2026)

## Abstract (arXiv)

The dominant paradigm in AI ethics and value alignment is highly anthropocentric. The focus of these disciplines is strictly on human values which limits the depth and breadth of their insights. Recently, attempts to expand to a sentientist perspective have been initiated. We argue that neither of these outlooks is sufficient to capture the actual complexity of the biosphere and ensure that AI does not damage it. Thus, we propose a new paradigm -- Biospheric AI that assumes an ecocentric perspective. We discuss hypothetical ways in which such an AI might be designed. Moreover, we give directions for research and application of the modern AI models that would be consistent with the biospheric interests. All in all, this work attempts to take first steps towards a comprehensive program of research that focuses on the interactions between AI and the biosphere.