Same model over timeSingle-run anecdoteAI Coding
Mentos and cola eruption simulation — Claude Opus 5.5 (Sep 30) vs Claude Opus 5.5 (Oct 20)
Scoreboard2
- Claude Opus 5.5Anthropic
- Written as “Opus 5.5”
- Top, labelled “OPUS 5.5 | SEP 30”
- Claude Opus 5.5Anthropic
- Written as “Opus 5.5”
- Bottom, labelled “OPUS 5.5 | OCT 20”
Prompt
Mentos and cola eruption simulationThe post doesn’t quote the prompt wording.
They say the Oct 20 rerun of the Sep 30 Mentos prompt came out worse, and ask whether Opus 5.5 was quietly nerfed.
@ivanainai’s view (paraphrased)
Claude Opus 5.5 runs the same Mentos-and-cola simulation prompt on Sep 30 and again on Oct 20, stacked top and bottom. The author says the Oct 20 run looks worse and asks whether the model was quietly nerfed.
Same model, same prompt, run on different dates: one sample each, not a controlled test. Model outputs vary from run to run, so the poster’s claim is not verified here. All same-model-over-time posts.
The post, itemised
- Kind
- Side-by-side
- Task
- Mentos and cola eruption simulation
- Category
- Simulations, 3D & Shaders
- Mode
- Not stated
- Posted
- Video length
- 19.8 s
- Likes
- 1,932
- Views
- 278,603
- Bookmarks
- 376
- Sponsored
- No
Related
Posted by @ivanainai on X. aivs.tv claims no ownership: it hosts a copy for fast playback and links to the post on X. Request removal
