Harness comparisonAI Coding
“The Last Streetlight” short in three agents — Claude Code (Claude Opus 5.5) vs Cursor (Muse Wonder 1.0) vs OpenAI Codex (GPT-6 Astra)
Video bySinda | SKatalyst AI@SKatalystAI · originally posted on X11 likes400 views
Claude Code with Claude Opus 5.5, Cursor with Muse Wonder and Codex with GPT-6 Astra each code a Pixar-style short about a robot, a cat and a rainy city, with no assets or libraries, then run three rounds of self-critique.
Each side pairs a coding harness with its own model, so harness and model differences are mixed. More Claude Code vs OpenAI Codex. More Claude Code vs Cursor. More OpenAI Codex vs Cursor. All harness comparisons.
The post, itemised
- Task
- “The Last Streetlight” short in three agents
- Category
- Animations/SVG
- Mode
- Not stated
- Posted
- Video length
- 60 s
- Likes
- 11
- Views
- 400
- Bookmarks
- 2
- Sponsored
- No
Cost & time, as stated in the postAs stated: 85 KB, 77 sec, 4.5–6/10; 32 KB, 60 sec, 6.2/10; 25 KB, 60 sec, 6.8/10. The scores are each system’s own self-critique, not an independent benchmark.
Related
Content belongs to its creators. Video by @SKatalystAI; aivs.tv hosts a copy for fast playback and links to the original post on X. Request removal
