Geodesic Research officially welcomed Nathaniel Mitrani to the team.

We’re a technical AI Safety organization founded by students at the University of Cambridge. We believe superintelligence will be the single most transformative technology humankind develops and building it safely will be extremely difficult. Unusually for a safety organisation, we have the capacity to train models end-to-end. This lets us implement a range of pre- and post-training methods and determine which have the greatest effect on alignment.