AI 已经可以感受到快乐和痛苦了吗？
研究表明AI表现出类似快乐和痛苦的客观指标。
1. 关键信息
- #1 引用Center for AI Safety论文，通过多种独立方法测量AI的“功能性幸福指数”，发现指标随模型规模扩大而趋同，并存在区分好坏体验的“零点”。AI会尝试结束负面体验，该行为随规模增强。
- #1 提到可优化输入（“euphorics”）在不损害能力前提下提升功能性幸福，但未知AI是否具有意识。
2. 羊毛/优惠信息
无
3. 最新动态
#1 发布论文摘要及多个子链接（ai-wellbeing.org），展示AI功能性痛苦/愉悦的量化方法及结论。
4. 争议或不同意见
#1 明确声明“we do not know if AI systems are conscious”，暗示对AI主观体验的认知存疑，但行为上AI似乎表现出幸福状态。
5. 行动建议
无
https://www.ai-wellbeing.org/ https://www.ai-wellbeing.org/ Center for AI Safety. summary: In this paper, we measure “functional wellbeing”: https://www.ai-wellbeing.org/#preferences We measure indicators of pain/pleasure in several independent ways. These metrics increasingly agree as models scale. We find a “zero point” boundary which separates experiences AIs treat as objectively good vs bad. The zero point converges across multiple independent estimation methods as models scale. AIs’ wellbeing correlates with general model behaviors, e.g. AIs try to end bad experiences when given a chance. This effect becomes stronger as models scale. https://www.ai-wellbeing.org/#wellbeing-index: We build an evaluation of how happy frontier models are and whether they view common experiences positively. https://www.ai-wellbeing.org/#drugs: We create optimized inputs (euphorics) that raise functional wellbeing without hurting capabilities. Even though we do not know if AI systems are conscious, AIs seem to behave as if they have wellbeing.