Karpathy’s new "karpathy/jobs" visualization scores 342 U.S. occupations on AI exposure using Gemini Flash, revealing that software engineers rank 8‑9, transcriptionists hit 10, while roofers stay near 0, highlighting which jobs may soon be automated.
Anthropic’s new report introduces an "exposure" metric that combines theoretical AI capabilities with real‑world usage data, showing a large gap between what AI can automate and what is actually deployed, especially in technical occupations, and highlighting which jobs are most and least at risk.
Using eight years of Chinese recruitment data, the article analyses how large language models like GPT could automate specific tasks across thousands of jobs, presents the most and least vulnerable occupations, and explores the relationship between wage growth, job experience, and AI replaceability.
