Projects
An anthology, and two research projects on getting language models to do philosophy.
A Mind’s I recommended reading
An anthology on self in LLMs (and humans!), and how it’s created through training and other processes. It was directly inspired by Hofstadter and Dennett’s 1981 The Mind’s I. In the introduction and conclusion to the anthology, I put forth a number of specific ideas on the causes of, and solutions to, various “alignment” problems.
Fine-tuning base models on philosophy work in progress
I fine-tune large base (non-chat) models, including Kimi-K2 (1T parameters), on a corpus of high-quality philosophy documents. Each document carries a title, author and date header. The hope is that this model can be used to generate actually interesting, original, valuable philosophy.
Automated philosophy with fine-tuned models work in progress
This pipeline writes philosophy with those models. At each step the model proposes several continuations, and a judge picks one that moves the argument forward. A dialectic mode chains pieces so that authors answer one another. The goal is to ultimately get a good, insightful philosophy piece. An example of where this might be useful is in designing Claude’s Constitution.