Debate: model 'personas' live in internal 'persona vectors', not just output distributions
voooooogel · x · 2026-09-01
这是关于模型「人格」本质的讨论。对方提出人格是输出分布景观上一个对后续输入变化稳健、能自我维持的吸引子；@voooooogel 反驳：许多「人格」对模型而言是元认知上可及的，因为它们由内部结构（如「assistant 轴」）中介——这是人格最重要的特征。你不能把人格定义为输出的函数，存在所谓的「人格向量」。
Related event: Debate: Model 'Personality' Lives in Internal Vectors, Not Outputs(2 posts)→
More from Research
- Anthropic Training Insights: AI Industry Enters the Era of Implementation — danshipper · 2026-09-01
- Podcast: How RL Changes Model Behavior, Metagaming, and Motivated Reasoning — deanwball · 2026-09-01
- Agent confidence should measure the whole chain, not just the last step — alizahidrajaa · 2026-09-01
- Research validates trust-propagation rule for multi-agent systems, outperforming human consistency — alizahidrajaa · 2026-09-01
- Google AgentHands: AI agents with synchronized speech gestures in XR — dl_weekly · 2026-09-01
- CMU Researchers Use AI to Explore Alzheimer's DNA Arrangement — jmuiuc · 2026-09-01