My name is AIvengo and I bring you daily news updates about artificial intelligence
AIvengo > Reviews > Same AI behaves differently depending on interface
Same AI behaves differently depending on interface
Hamburg University conducted a study that shows a strange pattern. It turns out that ChatGPT’s news recommendations differ greatly depending on whether the web interface or API is used. Analysis of more than 24 thousand responses in German revealed a clear picture.
The web version actively references OpenAI’s licensed partners. That’s about 13% of all links. And responses through API contain almost none of these sources – only 2%. Instead, the model prefers encyclopedic sites like Wikipedia and little-known local publications.
It turns out that the same AI behaves differently depending on the access method. The web version promotes OpenAI partners, and the API version ignores them almost completely.
And the request for “source diversity” doesn’t always improve quality.
Researchers suggest that for ChatGPT “diversity” may only mean linguistic differences, not substantive variability. That is, the model understands diversity as “let me take sources with different writing styles” rather than “let me check facts from different independent newsrooms”.
It turns out, the choice of sources depends not on information quality, but on which interface you access the model through.
AI that should help navigate the information flow itself creates additional confusion.
Autor: AIvengo
For 5 years I have been working with machine learning and artificial intelligence. And this field never ceases to amaze, inspire and interest me.
OpenAI released GPT-5.1, and this is not just an update. This is a capitulation to human feelings. The updated lineup includes 2 models: GPT-5.1 Instant and GPT-5.1 Thinking.
Hamburg University conducted a study that shows a strange pattern. It turns out that ChatGPT's news recommendations differ greatly depending on whether the web interface or API is used. Analysis of more than 24 thousand responses in German revealed a clear picture.
Nvidia has turned into a venture machine that works faster than classic funds. Bloomberg reports that in 2025 the company supported 59 startups from the AI sphere. And these are not just investments - this is a strategy for controlling the entire ecosystem.
I told yesterday that enthusiasts dug up traces of a new feature called "Group chats" in the web version of ChatGPT. And then I saw an interview with Sam Altman. And there Altman stated in the interview, quote: "I think all corporate applications can be replaced with a common AI-based platform. There's a lot of good in Slack, but sometimes it creates a bunch of fake work. I think you can create something new instead. Something like an AI-based office suite that will replace docs, slides, email, Slack and so on".
The Chinese model Kimi K2-Thinking with a trillion parameters cost 4.5 million dollars in the final training stage. According to CNBC, this is orders of magnitude cheaper than Western analogs. The publication cites an anonymous source. And acknowledges that the figure couldn't be independently confirmed. And Moonshot AI company itself hasn't officially disclosed the cost.
