AGI Strategies

person

Karthik Narasimhan

Princeton; reasoning, NLP

Princeton assistant professor of computer science. Previously a researcher at OpenAI before its scaling era. Focuses on language understanding and reasoning, and led work on the SWE-bench benchmark.

current Assistant Professor of Computer Science, Princeton University

Strategy positions

Evals-drivenendorses

Capability/risk evals gate deployment; evals are the load-bearing artefact

Argues evaluations grounded in real-world software engineering tasks reveal capability and safety properties that synthetic benchmarks miss.

SWE-bench evaluates language models in a realistic software engineering setting: resolving real GitHub issues from real codebases. Performance here is closer to deployment reality than synthetic tasks.
§ paperSWE-bench: Can Language Models Resolve Real-World GitHub Issues?· arXiv· 2023-10· faithful paraphrase

Closest strategy neighbours

by jaccard overlap

Other people whose strategy tags overlap with Karthik Narasimhan's. Overlap is on tag identity, not stance; opposites can show up if they reference the same tags.

  • Aleksander Mądry

    shared 1 · J=1.00

    MIT; ex-OpenAI head of preparedness

  • Alex Meinke

    Alex Meinke

    shared 1 · J=1.00

    Apollo Research; deceptive alignment evaluations

  • Ali Rahimi

    Ali Rahimi

    shared 1 · J=1.00

    Google Brain ML researcher; 'Alchemy' speech

  • Anna Rogers

    Anna Rogers

    shared 1 · J=1.00

    IT University of Copenhagen; LLM benchmarking critique

  • Arati Prabhakar

    Arati Prabhakar

    shared 1 · J=1.00

    White House OSTP director (2022–2025)

  • Beth Barnes

    Beth Barnes

    shared 1 · J=1.00

    Founder of METR; dangerous capability evaluations

Record last updated 2026-04-25.