返回资讯中心
外部精选
软件工程
#开发者实时流

These Neurons Control Territorial Claims

An LLM's answers depend on the beliefs built into it from its training data. Use an American LLM, you'll get an American view of the world. Use a Chinese LLM, you'll get a Chinese view of the world.

Hacker News 最新eob2026/10/27 · 今天3 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

An LLM's answers depend on the beliefs built into it from its training data. Use an American LLM, you'll get an American view of the world. Use a Chinese LLM, you'll get a Chinese view of the world.

This map shows an LLM's view of the world literally: Qwen3.5-4B's opinion of a selected set of regions. A 💥 means Qwen thinks it is disputed. A flag means Qwen thinks it is owned by someone non-standard.

Because Qwen is open-weight, we can trace its geopolitical claims to specific neurons in the LLM. Turning the volume up and down on these neurons changes how the LLM behaves when discussing geopolitics.

Select a neuron from the list below to see how stimulating that neuron, up or down, changes Qwen's view of the world's sovereignty. This "brain surgery" can be done on the fly while generating output.

One neuron at a time.Select a dot to compare its country claims.

NORTH AMERICASOUTH AMERICAEUROPEAFRICAASIAOCEANIA

Chosen to make the neuron's influence visible.

Choose another neuron to explore a change in territorial claims.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →