Hacker News Reader

I did a little test that I like to do with new models: "I have rectangular space of dimensions 30x30x90mm. Would 36x14x60mm battery fit in it, show in drawing proof". GPT5 failed spectacularly.

View on HN

I tried it again today out of curiosity. OpenAI said there was some routing bug on launch and requests were going to the cheaper model.

Today it seems pretty good. Not perfect, but not a spectacular failure.

https://chatgpt.com/s/t_68966fcf457c8191811968b9a6a2e81e

This was a fun prompt. I learned things from the models. Gemini 2.5 was wayy better than gpt5 here even though quite incomplete in the first response

Reply on news.ycombinator.com