Could AI feel pain? The answer is far more disturbing than you could imagine
Produced by: Mohsin Shaikh
Pain Choices
AI systems were tested with a game offering pain or pleasure as trade-offs, revealing complex decision-making behaviors.
Surprising Responses
Google’s Gemini 1.5 Pro always avoided pain, even at the cost of achieving fewer points.
Trade-Offs Studied
The study borrowed from animal behavioral research, using pain-pleasure dilemmas to analyze AI actions.
Human-Like Behavior
Some AI systems displayed nuanced choices, treating pleasure and pain in ways comparable to humans.
Ethical Concerns
The research by Jonathan Birch of LSE raises questions about AI sentience and the potential need for "AI welfare."
Credit: X
Animal Parallels
The study mirrors previous research on hermit crabs, suggesting AI may simulate behaviors akin to sentient beings.
Flawed Self-Reports
Researchers note that prior methods relying on AI self-reports are limited by potential mimicry rather than genuine experience.
Mimicked Sentience
AI might behave in seemingly sentient ways, but its responses could stem from training data, not true consciousness.
Future Testing
The study lays the groundwork for refined sentience tests, opening debates on AI rights and ethical implications.