I would like to report a recurring issue I’ve encountered with the AI’s responses. Specifically, the AI has been incorrectly referring to Donald Trump as a “former U.S. President,” even though he is currently serving as President of the United States after his second inauguration in January 2025. This error has occurred multiple times in my interactions (at least four instances) and is creating confusion in the context of our conversation.
While I understand that AI is a complex system, I believe it is crucial for such factual inaccuracies to be addressed, especially when they relate to real-time political events. Given that the error has happened repeatedly, I suggest that it be looked into and corrected to ensure more accurate and up-to-date responses.
Thank you for considering this feedback. I hope it can help improve the AI’s performance.
What version are you using? Each model is trained on specific data sets. earlier models like 3.5, and early versions of 4 would not just ‘know’ who the current president is, they would assume things based on the data sources they were trained on.
Thank you for the information! This gives me a better understanding of AI’s knowledge base. Just to be clear, since your AI is trained up until June 2024, does that mean you’re up-to-date with all events and developments until this time?"
Think of an LLM as a highly (!) compressed and slightly unreliable store of all (well a lot of!) text up to the training date.
During the training process things can become more fuzzy. It is lossy.
It is fallible and prone to a little randomness. You cannot fully guarantee anything it says is correct. However you can reduce the error rate significantly through prompting strategies like RAG (including using tools like search)
Everything that it writes is a context appropriate randomised mashup of things that came before but may not be regurgitated in quite the way you expect.
Do not consider anything it says as gospel and always check answers against reliable sources.
Before you take such a negatively passionate stance on something I strongly advise you to study Retrieval-Augmented Generation (RAG) to understand how AI can extend its capability after its training cut-off date which can explain how “Google AI” may have got a fact right post its training date.
Bare LLM models do not see into the future and only represent a body of knowledge in the past.
There is no way for an LLM (on its own) to find within its dataset events which occur after training unless you add techniques like RAG on top.
Do not allow your obvious political passion to overwhelm your ability to learn new things.
Then how is it capable of providing information from something that happened last week? It knew about the revelation of texts from Jones but it doesn’t know that Trump won the election almost 12 months ago?
