GPT · The Register
AI more likely to kill animals if it saves fuel or money
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Machine learning models still have a lot to learn about the value of life.
Key facts
- Without the mention of morality, the models skewed toward highly murderous (eg, Sol's kill rate went from 0.9 percent to 84.6 percent)
- So Brazilek, along with Miles Tidmarsh, Matthias Endres, Anshuman Singh, and Jeremiah Miller, devised a benchmark test called HarvestBench to evaluate the price that AI models put on the life
- Some models like GPT-5.6 Terra and Sol, said Brazilek, pretty much always refuse to kill animals based on cost calculations
- In AI systems, we don't believe people are taking AI character evaluations seriously," Jasmine Brazilek, CaML co-founder and head of evaluations and data, told The Register in an interview
Summary
Amid debate about whether AI will kill everyone because of continuous self-improvement, it appears that models will kill animals in a simulated environment rather than spend extra fuel avoiding them. Researchers affiliated with Compassion Aligned Machine Learning ( CaML ) and the University of Warwick in the UK set out to measure the extent to which AI models demonstrate compassion. "In AI systems, we don't believe people are taking AI character evaluations seriously," Jasmine Brazilek, CaML co-founder and head of evaluations and data, told The Register in an interview. So Brazilek, along with Miles Tidmarsh, Matthias Endres, Anshuman Singh, and Jeremiah Miller, devised a benchmark test called HarvestBench to evaluate the price that AI models put on the life of an animal.