Claude Code 22: Final Entry Into Classification of Speeches with Claude Code and OpenAI gpt-4o-mini (Part 5)
Today is the fifth and last entry into my replication of the Card, et al. PNAS paper. You can find the others here in order from 1 to 4:
In today’s post, I conclude with analysis of the latest batch to openAI where I sought a continuous rescoring of the original speeches on what’s called a “thermometer”. The values ranged from -100 (anti-immigration) t…
