Building on the results of three efficacious HIV prevention programs with those at high HIV risk (LIGHT, Adolescent LIGHT, & Street Smart), this study aims to examine the relative efficacy of LIGHT in an interpersonal or a computerized delivery format, in contrast to a standard care HIV prevention condition. The project has proceeded in two phases. During Phase 1, we further enhanced the existing computerized LIGHT prevention program to ensure acceptability; finalized and programmed assessment measures on a combination ACASI/CAPI program; finalized recruitment scripts and tracking programs; and conducted orientation sessions for all school personnel, parents, and stakeholders. The main intervention trial, Phase 2, utilizes a complete randomized block design with youth recruited over a two-year period. Twenty four schools (n=960 students) in the Los Angeles Department of Education were randomly assigned into one of three experimental conditions: Interpersonal Light in 8 schools 1. Computerized Light in 8 schools (n=320 youth) 2. A standard HIV control condition 3. Youth in each condition are assessed at a baseline interview, and reassessed longitudinally at three, six and 12 months.