Jeden z moich użytkowników doświadcza dziwnego zachowania podczas korzystania z Pomocy AI. Zaznacza pojedyncze słowo i wybiera opcję „Tłumacz na polski”. Interfejs użytkownika jest w języku polskim, a dzienniki błędów niczego nie pokazują.
What is the word? What is the LLM?
For example “vigilance” and “door jimmies.” The model being used is Gemini 2.0 Flash. As far as I can tell for now it seems to have been happening randomly
2개의 좋아요
Is this still the case?
We are working on moving to structured outputs at the moment, it should resolve issues like this.
1개의 좋아요
I totally forgot about this to be honest. I have since moved to GPT-4.1-mini but I just tested it again for good measure and this issue is no longer occurring.
1개의 좋아요
