Lasr Labs

London AI Safety Research Labs is a technical AI Safety research programme. Participants will work in teams of four, supervised by an experienced AI safety researcher, to produce a machine learning paper and accompanying blog post that makes incremental progress on an important problem in AI safety. Teams work full-time and in person from the London Initiative for Safe AI. The programme is designed to “learn by doing”; taking a research project from proposal all the way to publication. The programme was previously run by AI Safety Hub when four out of five groups had papers accepted to workshops (at NeurIPS) or conferences (ICLR). Three past participants now work at the UK AI Safety Institute, one works on Open AI’s dangerous capabilities evals team, and several have continued collaborating with their supervisors or are doing AI safety work in PhD programmes at top universities.