Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Yea I see this a lot with Gemini since 2.5

Very stubborn and “opinionated”

I think most models will tend this way (to consolidate more control over how we “think” and what we believe)



Went over my last conversations with Gemini 2.5 and asked the same things to GPT-5 with thinking on, the latter was consistently worse both in content and form.

I wouldn't have guessed Gemini to win the AI race in 2025 but here we are.


I would be surprised if they didn't, just from the difference in number of employees and resources. Google can pursue 20x as many dead ends, anthropic and openai have to commit to a few things and hope they're right




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: