Skip to content
Rohan Mehta

Rohan Mehta

AI / ML Engineer

Rohan builds LLM-powered products at Q Technologies, from retrieval-augmented chatbots to evaluation pipelines. He writes about making generative AI reliable enough for real businesses.

Generative AILLMsRAGAI EvaluationPythonLinkedInGitHub

1 article by Rohan Mehta

Illustration of an AI chat bubble with a confident but incorrect answer

Artificial Intelligence

What Are AI Hallucinations? Why Generative AI Makes Things Up

An AI hallucination is output that sounds plausible and confident but is false, invented or not supported by the information the model was given. It happens because generative models predict likely text instead of looking up facts, and it can be reduced, though not eliminated, with grounding, tools and verification.

Rohan Mehta

Rohan Mehta

· 7 min read