Matthew Shinkle

By design, LLMs perform nonlinear mappings from their inputs (text sequences) to their outputs (next-token generations). Nonlinearities are built into the model architecture, but the way models use these nonlinearities in their representation of information is still an open question. By studying different aspects of this nonlinear mapping, we can...

There have been multiple recent calls for the automation of AI safety and alignment research. There are likely many people who would like to contribute to this space, but would benefit from clear directions for how to do so. Stemming from a recent SPAR project and in light of limitations...