A moose playing Go in a park while drinking boba
Read OriginalThe author tests the Sora 2 AI video generation model using a complex prompt: 'a moose playing Go in a park while drinking boba.' The article details the consistent failures and limitations of AI in rendering this scene, including anatomical inaccuracies, logical errors in the Go game, and unsettling visual artifacts, providing a critical look at the current state of AI video generation.
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
1
Introducing GPT-5.1 for developers
Simon Willison
•
6 votes
2
🧠 Build an Agent Chat that Remembers — Persisting Conversations with Microsoft Agent Framework
Bruno Capuano
•
3 votes
3
ServiceNow and Microsoft Copilot
Marius Sandbu
•
2 votes
4
Cursor 2.0 and Composer Model
Codeaholicguy
•
2 votes
5
A simple explanation of the big idea behind public key cryptography
Richard Gendal Brown
•
1 votes
6
Google Antigravity Exfiltrates Data
Simon Willison
•
1 votes
7
8
Fix “This video format is not supported” on YouTube TV
David Walsh
•
1 votes
9
Tooltip Components Should Not Exist
TkDodo Dominik Dorfmeister
•
1 votes
10
llm-anthropic 0.22
Simon Willison
•
1 votes