Abhishek Nagaraj

@abhishekn

Associate Prof @berkeleyhaas, NBER RA. Dad to 2 girls. he/him/his. Interested in using tech, AI and data to drive progress. Using ideas as my maps.

following
followers

A research agenda to steer AI beyond automation

The essay’s authors argue that computer science culture, not just economic incentives, helps explain AI’s automation focus.

9 Sources, 5d ago, updated 5d ago

Mechanistic interpretability methods for social simulations with AI agents

A post announces a new paper on bringing mechanistic interpretability methods to AI-agent social simulations, with a link to arXiv.

1 Source, 35d ago, first seen 35d ago

ORQA working paper proposes a framework for assessing LLM knowledge across occupations

One of the paper’s authors presents ORQA as a way to tackle the difficult, costly task of evaluating large language models’ capabilities across the full range of occupations.

2 Sources, 36d ago, first seen 36d ago

Featured in

A research agenda to steer AI beyond automation

Mechanistic interpretability methods for social simulations with AI agents

ORQA working paper proposes a framework for assessing LLM knowledge across occupations

Featured in

A research agenda to steer AI beyond automation

Mechanistic interpretability methods for social simulations with AI agents

ORQA working paper proposes a framework for assessing LLM knowledge across occupations