Remix.run Logo
sarreph 2 hours ago

I had intended to caveat that: I'm sure I'm not the first person to ask about this!

> you still see improvements

This is expected if they are training their models on it, right?

> objectively-bad results

Keen to learn when this has been the case, i.e. across version increments in major models.

simonw 2 hours ago | parent [-]

I've written about this a couple of times, most notably here: https://simonwillison.net/2025/Nov/13/training-for-pelicans-...

I've been enjoying seeing how the quality of individual models differ based on the amount of reasoning effort you give them. If they were baking an a good pelican you wouldn't expect them to differ so much.

(Google Gemini are the only lab that have very clearly paid attention to the quality of SVG animals-riding-vehicles, see their announcement for Gemini 3.1: https://twitter.com/JeffDean/status/2024525132266688757 )

sarreph 2 hours ago | parent [-]

Amazing, thank you Simon! Look forward to reading.

38484858 2 hours ago | parent [-]

[flagged]