A new Lancet Psychiatry review examined 54 randomized trials of cannabinoids for mental disorders and substance use disorders, and the evidence was thinner than many public claims suggest. A few outcomes showed signals, especially in cannabis use disorder, sleep-time outcomes in insomnia, tic severity, and autism-related measures, but much of the literature remained low certainty and short-term. This physician-guided review explains what the paper actually found, what it did not test, and how to think about the gap between clinical enthusiasm and evidence quality.