GPT 4 may be smarter than ChatGPT but it can cook up fake stories, make wrong predictions

After months of speculation, OpenAI has unveiled the GPT-4, which is a successor to the GPT-3, which powers the ChatGPT. The GPT 4 is smarter, has cracked some of the toughest examinations, but the smartest AI language model in town still makes the same mistakes it’s predecessor made. Highlighting the limitations of GPT 4, OpenAI in its blog stated, “Despite its capabilities, GPT-4 has similar limitations as earlier GPT models. It “hallucinates” facts and makes reasoning errors,” The company also asked users to be careful when using language model outputs, particularly in “high-stakes contexts, with the exact protocol matching the needs of a specific use-case.” That being said, OpenAI noted in the blog that the GPT-4 model is more reliable than the GPT 3 model. Among other limitations, the OpenAI highlights that the language model may not have accurate information about the events taking place in 2023.