Large-scale language models (LLMs), such as the GPT-4 from OpenAI and the Pathways Language Model from Google, have become indispensable to our daily lives and work, frequently being used without our conscious knowledge. Though study indicates that even crowdsourcing professionals have trouble identifying human-generated content from AI-generated content, subtle defects in AI writing continue to make this tough to perform. Even though these models have many benefits and the potential to totally change the way people work and learn, they have also drawn a lot of attention due to their potential drawbacks. One notable use of LLMs that demonstrates their potential for task automation is the generation of academic reports or articles with little to no human input. As a result, scientists have concentrated on creating detectors to deal with possible wrongdoing related to information provided by LLM. However, current methods frequently ignore the vital component of generalizability in favor of accuracy on small datasets. Our study offers a thorough examination of machine learning (ML) techniques that are intended to differentiate text produced by artificial intelligence (AI) from language created by humans. We attempt to use a Kaggle dataset in order to gain greater insight into the data collection procedure. To address the challenge of accurately and reliably detecting text produced by artificial intelligence (AI), we explore various machine learning approaches. We examine a broad spectrum of algorithms taking into account performance measures and their generalizability to different datasets and scenarios. By providing a more thorough explanation of the significance of LLMs, the challenges they provide, and the specific focus of our study, we broaden the abstract and lay the foundation for a thorough analysis of ML algorithms for text identification.