Artificial intelligence (AI), coupled with machine learning (ML) has been rapidly incorporated into pharmaceutical discovery and development. We reviewed 53 publications from 2018-2026 to summarize current applications of AI/ML in drug discovery. AI and ML have potential to impact every step of the drug development pipeline and have already shown to drastically reduce time frames for developing therapeutics. Specific deep learning models such as graph neural networks and transformers have shown promise in de novo molecular generation, molecular property prediction, and target recognition. Accurate protein structure prediction using AlphaFold allows for exploration of drug-target binding. De novo drug design with reinforcement learning allows for targeted design of molecules with desired properties. Machine learning models for QSAR provide more accurate toxicity predictions and ADMET profiling to avoid potential failures during drug development. However, current limitations include lack of interpretability, data limitations, and lack of regulatory approval. According to a review of recent literature, AI has the potential to decrease the time required for drug discovery from years to months and lower the cost of drug development. This review discusses recent advances, successful clinical examples, and opportunities for artificial intelligence/machine learning in drug discovery.