# 访谈 LTX 联合创始人兼 CTO Yaron Inger，检验 LTX-2.5 的世界模型主张

- 来源：Chubby♨️ (@kimmonismus)
- 发布时间：2026-09-02 21:12
- AIHOT 分数：44
- AIHOT 链接：https://aihot.virxact.com/items/cmtk565yf01pfrodu1rhzj7gc
- 原文链接：https://x.com/kimmonismus/status/2095137667570716711

## AI 摘要

作者与 Peter 对话 LTX 联合创始人兼 CTO Yaron Inger，围绕其新开放权重的视频与世界模型 LTX-2.5 展开讨论。问题包括模型在生成逼真画面之外实际理解了什么、物理能力是否足够支撑机器人领域、原生多镜头生成在剪辑间记住了什么、速度基准是否公平、创作者在可负担硬件上的预期，以及开放下载权重后 LTX 如何构建商业模式。

## 正文

AI video companies are no longer claiming they can simply generate better clips.

They are claiming their models understand the world.

So Peter and I put that claim to the test.

We sat down with Yaron Inger, Co-Founder and CTO of @ltx_io , for a direct conversation about LTX-2.5, its new open-weights video and world model.

We asked what the model actually understands beyond producing plausible frames. Whether its physics are good enough for robotics. What native multi-shot generation really remembers across cuts. Whether its speed benchmarks are fair. What creators can expect on hardware they can realistically afford. And how LTX plans to build a business when the weights are available to download.

This is not a product demo. It is a conversation about whether AI video is becoming genuine infrastructure for filmmaking, simulation, and physical AI.

Watch the full interview: