← 返回归档

帖子详情

查看 X 原文
O
elvis@omarsar0
Pay attention to this new wave of VLMs. Glimpse is the first model from @ElorianAI , the brains that led Google's Gemini and Apple's MM-1. Quick test: 10 game boards from an overhead camera. Same prompt, same image, two models, hand-checked. Glimpse: 8/10 boards fully correct. Gemini 3.8 Flash: 5/10. This is what data labeling looks like. Getting the whole frame right, not just most of it, turns raw robot footage into training data. This is powerful Visual Thinking, not just visual recognition translated into text. 🔗 View on Twitter Andrew M. Dai @AndrewDai Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that. Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks. 🔗 View on Twitter 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
▶ 打开视频地址▶ 打开视频地址
帖子 ID
2111145857995158012
Markdown
/app/data/archive/2026/10/16/omarsar0/2111145857995158012/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111145857995158012"
author: "omarsar0"
published_at: "2026-10-16T17:22:50+00:00"
source_url: "https://x.com/omarsar0/status/2111145857995158012"
---

Pay attention to this new wave of VLMs.  
  
Glimpse is the first model from [@ElorianAI](https://x.com/ElorianAI), the brains that led Google's Gemini and Apple's MM-1.  
  
Quick test: 10 game boards from an overhead camera. Same prompt, same image, two models, hand-checked.  
  
Glimpse: 8/10 boards fully correct.  
Gemini 3.8 Flash: 5/10.  
  
This is what data labeling looks like. Getting the whole frame right, not just most of it, turns raw robot footage into training data.  
  
This is powerful Visual Thinking, not just visual recognition translated into text.

[🔗 View on Twitter](https://x.com/omarsar0/status/2111145857995158012/video/1)

![Andrew M. Dai](https://pbs.twimg.com/profile_images/1098666487718436865/NVcU35fX_normal.png)

Andrew M. Dai@AndrewDai

Spent years watching models ace a single image and completely whiff on anything that moves or changes angle. Today we’re fixing that.  
  
Try Glimpse now, our first visual thinking model with competitive frontier performance compared to Astra on key public visual reasoning benchmarks.

[🔗 View on Twitter](https://x.com/AndrewDai/status/2111142161584628060/video/1)

[🔗 View Quoted Tweet](https://x.com/AndrewDai/status/2111142161584628060)

## 视频地址

- [视频 1](https://video.twimg.com/amplify_video/2111145533762940929/vid/avc1/1920x1080/NH3uKXusy6B0Gm0H.mp4?tag=29)
- [视频 2](https://video.twimg.com/amplify_video/2111141984752779264/vid/avc1/1920x1080/Gg2DIERzkoz-Ds-n.mp4?tag=29)