The World Health Organization recommends same-day initiation of antiretroviral therapy (ART) for all persons diagnosed with HIV and ready to start treatment. Evidence, mainly from randomized trials, indicates offering same-day ART increases engagement in care and viral suppression during the first year. In contrast, most observational studies using routine data find same-day ART to be associated with lower engagement in care. We argue that this discrepancy is mainly driven by different time points of enrollment, leading to different denominators. While randomized trials enroll individuals when tested positive, most observational studies start at the time point when ART is initiated. Thus, most observational studies omit those who are lost between diagnosis and treatment, thereby introducing a selection bias in the group with delayed ART. This viewpoint article summarizes the available evidence and argues that the benefits of same-day ART outweigh a potential higher risk of attrition from care after ART initiation.