ObjectiveThe aim was to test if people with different alcohol use problem severity benefitted differentially from brief alcohol interventions delivered in-person versus through computer-generated feedback letters. MethodsNine hundred sixty-one 18–64year old general hospital inpatients with at-risk alcohol use (mean age=40.9years [standard deviation=14.1], 75% men) were randomized to a) in-person counseling, b) computer-generated individualized feedback letters, or c) assessment only. Both interventions were delivered on the ward and 1 and 3 months later. Outcome was the change in the self-reported alcohol use per day at 6-, 12-, 18-, and 24-month follow-up. The Alcohol Use Disorder Identification Test (AUDIT) score was tested as a moderator of the effect of in-person counseling and computer-generated feedback letters, with higher AUDIT scores indicating more severe alcohol problems. ResultsCompared to assessment only, computer-generated feedback letters more strongly reduced alcohol use over 24 months among persons with AUDIT scores of about 8 and lower (ps <0.05). In-person counseling tended to be superior over assessment only among persons scoring high on the AUDIT, but differences were not statistically significant. Six-, 12-, and 18-month differences between in-person counseling and computer-generated feedback letters were significant (ps<0.05) for persons with AUDIT scores below 7.1–7.7. The differences between both interventions attenuated at 24-month follow-up. ConclusionsComputer-based intervention delivery may be superior over in-person delivery for people with low levels of alcohol use problem severity, whereas those with more severe alcohol problems may require more intensive care.