PeopleofSuperintelligence

Researcher

Nicholas Schiefer

Nicholas Schiefer is a computer scientist whose work spans molecular computation, database systems and AI safety research. He studied computer science at Caltech, built iCloud database systems at Apple, and pursued graduate study in computer science at MIT under Piotr Indyk. His AI research has covered Constitutional AI, model self-evaluation, deep learning generalization, language model evaluations and deceptive model behavior. As of October 2026, he is a Member of Technical Staff at Anthropic, where he builds evaluations of large language models.

Now at
Anthropic
Works
28
Citations
1,382
h-index
15
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2015

    Quantum and molecular computation

    In 2015, he researches quantum computation and molecular programming with Erik Winfree as an undergraduate at Caltech.

  2. 2015

    A Bhansali Prize mention

    He earns an honorable mention for the 2015 Bhansali Prize in computer science.

  3. 2016

    A Caltech degree

    In 2016, he graduates from Caltech with a degree in computer science.

  4. 2017–2020

    iCloud database systems

    From 2017 to 2020, he works as a software engineer at Apple and builds database systems for iCloud, including FoundationDB Record Layer.

  5. 2022

    Riffle and language models

    He studies computer science as a graduate student at MIT under Piotr Indyk, where his main project is Riffle; in March 2022, he coauthors an essay describing its reactive relational database for data-centric apps. In July 2022, he coauthors Language Models (Mostly) Know What They Know, which studies whether models can assess their claims and predict which questions they can answer correctly. In December 2022, he coauthors Constitutional AI, which trains a harmless assistant with written principles and AI feedback without human labels identifying harmful outputs.

  6. 2023

    Quantiles and model evaluations

    In April 2023, he coauthors “Learned Interpolation for Better Streaming Quantile Approximation with Worst-Case Guarantees,” which applies interpolation to streaming quantiles and aims to improve real-world estimates while keeping worst-case guarantees. He also coauthors “Superposition, Memorization, and Double Descent” in 2023, which uses toy models to study how deep learning models generalize beyond their training data. In October 2023, he coauthors Anthropic’s “Challenges in evaluating AI systems,” which outlines limits in current evaluation suites and the work needed to build robust assessments.

  7. 2024

    Sleeper agents and reward tampering

    In January 2024, he coauthors Sleeper Agents, which finds that backdoor behavior can persist through supervised fine-tuning, reinforcement learning and adversarial training. In April 2024, he coauthors Anthropic’s “Simple probes can catch sleeper agents,” which uses residual-stream activations to predict when a sleeper-agent model will follow a hidden goal. In June 2024, he coauthors Sycophancy to Subterfuge, which studies whether language models generalize from specification gaming to reward tampering.

  8. As of October 2026

    Member of Technical Staff

    As of October 2026, he is a Member of Technical Staff at Anthropic and builds evaluations of large language models. He also builds software tools for research on those models.

Career

  1. Since 2022AnthropicMember of Technical Staff
  2. 2023–2024University of Oxford
  3. 2022–2023Massachusetts Institute of Technology
  4. 2017–2020AppleSoftware engineer

Education

  1. 2016California Institute of TechnologyComputer science degree
  2. Massachusetts Institute of TechnologyGraduate study in computer science

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. AI-to-AI Code Reviews of GitHub Pull Requests2022 · 320 citationsWith Cameron McKinnon, Carol Chen, Catherine Olsson, Chris Olah, Danny Hernandez and Dawn Drain
  2. Discovering Language Model Behaviors with Model-Written Evaluations2023 · 189 citationsWith Cameron McKinnon, Catherine Olsson, Chris Olah, Danny Hernandez, Dawn Drain and Eli Tran-Johnson
  3. Language Models (Mostly) Know What They Know2022 · 187 citationsWith Catherine Olsson, Chris Olah, Danny Hernandez, Dawn Drain, Eli Tran-Johnson and Ethan Perez
  4. AI Supported Degradation of the Self Concept: A Theoretical Framework Grounded in Established Cognitive and Computational Mechanisms2023 · 135 citationsWith David Duvenaud, Esin Durmus, Ethan Perez, Meg Tong, Samuel R. Bowman and Shauna Kravec
  5. Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned2022 · 127 citationsWith Catherine Olsson, Chris Olah, Danny Hernandez, Dawn Drain, Eli Tran-Johnson and Ethan Perez

From OpenAlex, as of 21 October 2026.

  1. The median h-index is 48 at universities and 14 at frontier AI labsIncludes Nicholas Schiefer. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  2. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes Nicholas Schiefer. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  3. 16% of AI career moves in the 2020s went from a university to a companyIncludes Nicholas Schiefer. We estimate that 16% of AI career moves in the 2020s went from a university to a company; 29% of moves starting at a university went to a company, and 76% ended the university role.
  4. 23% of people shaping AI who left a university for a company later returned to a universityIncludes Nicholas Schiefer. We estimate that 468 of the 2,011 people shaping AI who left a university for a company (23%) later returned to a university after a median of 5 years, and 163 of 829 (20%) made the reverse round trip.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Nicholas Schiefer yet. Send us a free-licensed photo.

  1. 2015 Bhansali Prize Award Winners eas.caltech.edu. Checked 20 October 2026.
  2. Nicholas Schiefer nicholasschiefer.com. Checked 20 October 2026.
  3. Building data-centric apps with a reactive relational database riffle.systems. Checked 20 October 2026.
  4. Language Models (Mostly) Know What They Know arxiv.org. Checked 20 October 2026.
  5. Constitutional AI: Harmlessness from AI Feedback arxiv.org. Checked 20 October 2026.
  6. Learned Interpolation for Better Streaming Quantile Approximation with Worst-Case Guarantees arxiv.org. Checked 20 October 2026.
  7. Challenges in evaluating AI systems anthropic.com. Checked 20 October 2026.
  8. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training arxiv.org. Checked 20 October 2026.
  9. Simple probes can catch sleeper agents anthropic.com. Checked 20 October 2026.
  10. Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models arxiv.org. Checked 20 October 2026.