News for hackers. Stuff that matters.

A comment on Vision Language Models Are Biased. Parent comment

Re:Vision Language Models Are Biased by inerte on Tuesday June 03, 2025 @02:57PM (#44173383)
I took a screenshot of the chicken, so low res, and got {4} https://chatgpt.com/share/683f4506-ae18-800f-8c27-5c5e91429a...

Also I think the authors used the API, and maybe there are differences between the API and chatgpt.com behavior...

[ Parent | on HN ]
Re:Vision Language Models Are Biased by simonw on Tuesday June 03, 2025 @04:05PM (#44174122)
ChatGPT is running a special model but it's also available through the API: https://platform.openai.com/docs/models/chatgpt-4o-latest

The system prompt may still make a difference though.

[ Parent | on HN ]
Re:Vision Language Models Are Biased by runako on Tuesday June 03, 2025 @03:38PM (#44173799)
I could rant for quite a while about how OpenAI and Anthropic manage their apps vs their APIs. It's really quite strange that they both landed on the solution of non-public APIs that perform differently than their public APIs.
[ Parent | on HN ]
Re:Vision Language Models Are Biased by anguyen8 on Tuesday June 03, 2025 @05:02PM (#44174702)
https://imgur.com/cO7eFNt

o3 Chat is also similarly wrong, saying {4}.

[ Parent | on HN ]