---
id: 20261117-T0-16
title: "Black Forest Labs两位创始人谈如何从像素、运动与声音中学习AGI"
title_en: "Black Forest Labs Founders Make the Case for Learning AGI from Pixels"
url: https://ai.daily.yangsir.net/daily/20261117-T0-16
issue_date: 2026-11-17
publish_date: 2026-11-16T21:38:03.000Z
category: insight
source_name: "Latent Space"
source_url: https://latent.space/p/bfl/
---

# Black Forest Labs两位创始人谈如何从像素、运动与声音中学习AGI

Black Forest Labs联合创始人Andreas Blattmann和Dustin Podell在访谈中阐述公司路线：从像素、运动和声音中学习通向AGI。他们的核心论点是视觉与多模态信号应成为智能学习的主要来源，而非仅依赖文本。两人此前参与开发Stable Diffusion系列，新公司继续在生成模型方向推进。对关注多模态模型走向的读者，这场对话提供了与主流语言模型路线不同的视角。

## English Version

**Black Forest Labs Founders Make the Case for Learning AGI from Pixels**

Black Forest Labs co-founders Andreas Blattmann and Dustin Podell laid out their case for learning AGI from pixels, motion, and sound in a Latent Space interview. Their argument: visual and multimodal signals should be a primary source of intelligence learning, not just text. Both previously worked on the Stable Diffusion series and are continuing in generative models. The conversation offers a counterpoint to the text-centric path dominant among frontier labs.

---

**来源**：[Latent Space](https://latent.space/p/bfl/)

**详情页**：https://ai.daily.yangsir.net/daily/20261117-T0-16

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*