Hi there 👋

We estimate how labor markets in 141 countries are exposed to frontier AI, showing large cross-country variation, gender gaps, adoption correlations, and remittance-linked indirect exposure.

We compare prompting, sparse autoencoders, and linear probes for interpreting and controlling LLM agent behavior in social science simulations. SAE-based steering outperforms prompting, offering fine-grained, predictable control over preferences and capabilities.

This is the first ever paper that I have contributed to, we did this exactly an year back.