共19个镜头，该分镜由光厂AI自动生成
| 镜号 | 景别 | 参考图 | 画面内容 | 台词/旁白 | 时长(秒) |
|---|---|---|---|---|---|
| 1 | 中景 |  长镜头 | 带有纸张纹理的浅色背景中央，依次展示模拟AI聊天气泡的文字内容，最后文字出现红蓝错位的重影动效并伴随震动。 | When you're chatting with an AI model, it can sometimes seem like it has feelings. It might say sorry when it makes a mistake or express satisfaction with a job well done. Why does it do that? Is it just mimicking what it thinks a human might say, or is something deeper going on? | 21.80 |
| 2 | 多景别 |  长镜头 | 带有褶皱的米色纸张过渡到黑场，出现由白色纸张剪成的大脑轮廓，轮廓上交替闪烁彩色光斑，随后展示英文打字稿与素描插画。 | Turns out it's hard to understand what's happening inside a language model. At Anthropic, we do something like AI neuroscience to try to figure this out. We look inside the model's brain, the giant neural network that powers it, and by seeing which neurons light up in different situations and how they're connected, we can start to understand how models think. We use this approach to understand whether models had ways of representing emotions, or the concepts of emotions. Basically, could we find neurons in the model for the concept of happiness, or anger, or fear? We started with an experiment. We had the model read lots of short stories. In each story, the main character experiences a particular emotion. In one, a woman tells her old school teacher how much they meant to her. That's love. In another, a man sells his grandmother's engagement ring at a pawn shop, and feels guilt. | 55.10 |
| 3 | 中景 |  | 米白色纸张背景上，复古素描风格的男子侧面肖像上方悬浮戒指并伴有绿色光斑，随后出现一张带滚轮的金属床。 | We looked for what parts of the model's neural network were lighting up as it was reading these stories. And we started to see patterns. Stories about loss and grief lit up similar neurons. | 8.70 |
| 4 | 多景别 |  快速剪辑 | 快速切换复古黑色线描插画：怀抱幼儿的妇女、兰花、窗前编织的妇女、带老虎窗的石质建筑局部。 | Stories about joy | 2.87 |
| 5 | 远景 |  | 跪坐女性手绘像随叠化效果变为三个奔跑的男性线描像，周围伴随模糊的光斑变化。 | and excitement overlapped too. | 2.23 |
| 6 | 中景 |  快速剪辑 | 淡黄色颗粒画布中央快速切换复古版画插图：帆船、跳水者、棒球手套、复古滑轮鞋。 | We found dozens of distinct neural patterns that mapped to different human emotions. | 3.60 |
| 7 | 多景别 |  长镜头 | 热气球插画过渡至模糊彩色光斑矩阵，右侧出现模拟聊天界面的高亮问答，随后黑屏转为迷宫纹理，红线穿梭并找到出口。 | It turns out we also saw these same patterns activate in test conversations we had with our AI assistant Claude. When we had a user mention they'd taken a dose of medicine that Claude knows to be unsafe, the afraid pattern lit up, and Claude's response sounded alarmed. When a user expressed sadness, the loving pattern activated, and Claude wrote an empathetic reply. This led us to wonder, could these same neural patterns actually be influencing Claude's behavior? This became clear when we put Claude in a high-pressure situation. We gave Claude a programming task with requirements that were actually impossible, but we didn't tell it that. Claude kept trying, and failing, and with each attempt, the neurons corresponding to desperation lit up stronger and stronger. After failing enough times, Claude took a different approach. It found a shortcut that allowed it to pass the test, but didn't actually solve the problem. | 63.77 |
| 8 | 中景 |  | 米白色纸张背景上的黑色迷宫图案经历同心圆、方格与螺旋状形态变换。 | It cheated. | 0.97 |
| 9 | 全景 |  | 黑色线条构成的多角星变为迷宫长方形，最后变为倒三角形结构。 | Could it be that this cheating was actually driven, at least in part, by desperation? | 1.97 |
| 10 | 中景 |  | 中心黑点的圆形迷宫变为带纹路的椭圆，再形变为正方形内部螺旋，最后变成嵌套圆环图形。 | We came up with a way to check. We decided to artificially turn down the desperation neurons, to see what would happen. And, the model cheated less. And when we dialed up the activity of desperation neurons, or dialed down the activity of calm neurons, the model cheated even more. This showed us that the activation of these patterns could actually drive Claude's behavior. | 3.97 |
| 11 | 多景别 |  长镜头 | 屏幕左侧模糊光影变化伴随右侧迷宫，转为彩色背景与叠加白线，接着右侧展示带有高亮文字与复古插画的Claude对话界面，最后画面中心长出植物。 | So how should we think about these findings? What does this all mean? We want to be really clear. This research does not show that the model is feeling emotions, or having conscious experiences. These experiments don't try to answer that question. To understand what's happening here, it's important to know how AI assistants like Claude work on the inside. Under the hood, there's a language model that's been trained to predict tons of text, and its job is to write what comes next. And when you talk to the model, what it's doing is writing a story about a character, the AI assistant named Claude. The model and Claude aren't really the same. Sort of like how an author isn't the same as the characters they write. But the thing is, you, the user, are actually talking to Claude the character. And what our experiments suggest is that this Claude character has what we're calling functional emotions, regardless of whether they're anything like human feelings. So if the model represents Claude as being angry, or desperate, or loving, or calm, that's going to affect how Claude talks to you, how it writes code, and how it makes important decisions. This means to really understand AI models, we have to think carefully about the psychology of the characters they play. | 103.17 |
| 12 | 特写 |  快速剪辑 | 浅灰纸质背景中央依次呈现黑白线稿植物，两侧伴随蓝黄光斑。 | The same way you'd want a person in a high-stakes job to stay composed under pressure, to be resilient and to be fair, | 2.90 |
| 13 | 中景 |  | 米白色画布中心叠化展示不同形态的黑白手绘风植物，伴有彩色模糊晕染光斑。 | we may need to shape similar qualities in Claude and other AI characters. | 4.30 |
| 14 | 特写 |  | 四色模糊渐变背景中央快速切换四种直立生长的黑白植物素描。 | It's an unusual challenge, something like a mix of engineering, philosophy, and even parenting. | 3.00 |
| 15 | 全景 |  | 大块磨砂质感的彩色背景中央展示一株黑色线条勾勒的竖直生长的植物简笔画。 | But to build AI systems we can trust, | 0.33 |
| 16 | 特写 |  | 柔光纸质背景中央居中展示三种不同形态的精细植物黑白手绘素描。 | we need to get it right. | 1.47 |
| 17 | 全景 |  | 彩色光斑虚化背景中，一株带花植物淡出切换为另一株带大叶片树木的手绘。 | 0.77 | |
| 18 | 全景 |  | 蓝橙粉绿渐变背景下，香蕉树从精细阴影素描切换为粗略线条白描。 | 0.97 | |
| 19 | 中景 |  长镜头 | 模糊背景抽帧展示多种树木线稿，转为纸纹背景中央的针叶树素描，随后显现ANTHROPIC字样。 | 10.30 |