Inside the Black Box: Cracking AI and Deep Learning

The Pattern Holds for Another Author


Listen Later

We trained a fresh LoRA on the letters of Seneca and ran the same analysis pipeline we used on Marcus Aurelius and advertising copy. Every structural finding replicated. The model organizes its adaptation into five clusters: one tight (features moving in lockstep) and four loose (features cooperating more independently). Seneca produced the cleanest clustering we've measured and the strongest workhorse cluster, a group of 141 features encoding philosophical argumentation with a causal effect more than three times stronger than anything in Marcus. Done in collaboration with John Holman.
...more
View all episodesView all episodes
Download on the App Store

Inside the Black Box: Cracking AI and Deep LearningBy Jellypod