# AI model limitations ## What are the limitations of PreGPT ? Like all chatbots, PreGPT 2.0 has its boundaries. It does not provide real-time or web-based information and operates with knowledge up until roughly Spring 2023, when the Mistral 7B training data ended. Venice.AI's models are built over with Major languages are supported by current models. ## What about AI hallucinations ? PreGPT 2.0, on occasion, may produce clearly incorrect or irrelevant responses. This phenomenon, known as "AI hallucination," is due to factors like limited training data or inherent biases. When experienced, try to clarify your prompt. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.presearch.io/pregpt/faq/ai-model-limitations.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.