Pith. sign in

Researcher Evidence Record

Amanda Askell

This bounded record lists 22 Pith paper rows and 0 imported work rows attributed to this corpus identity. The enumerated, non-disputed paper rows include cs.CL, cs.CY, cs.CR work dated 2019 to 2025. The record describes sources and coverage; it makes no judgment about the person.

Compiled coverage vector

Measured lane counts only. Not a trust score or person verdict.

Identity 2 canonical identity row plus typed public identifiers Pith papers 22 attributed paper rows in the Pith corpus, itemized below Imported works 0 imported works beyond the paper ledger Current reviews 18 of 22 papers carrying a current Pith review; presence, not outcome Sourced citations 22 of 22 works with a source-named citation count Coauthors 50 distinct coauthors across shared paper rows
Enumerated paper scope: 6 fields (cs.CL, cs.CY, cs.CR, +3 more) · 2019-2025 sources: authors, author_identifiers · paper_authors · author_works · current_verdicts · cited_works

A sourced case file for attributed work. It is neither a profile score nor a verdict about this researcher.

Attributed works

A bounded ledger from the Pith paper and imported-work queries. Counts and source confidence stay with each work.

  1. 2025 Pith paper

    Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    11
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 36 pith inbound references from cited_work_pith_inbound_counts
  2. 2024 Pith paper

    Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

    cs.CR provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    paper_authors
    Printed name
    Amanda Askell
    Author position
    12
    Identity state
    provisional
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 104 pith inbound references from cited_work_pith_inbound_counts
  3. 2023 Pith paper

    Specific versus General Principles for Constitutional AI

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 5 pith inbound references from cited_work_pith_inbound_counts
  4. 2023 Pith paper

    Towards Understanding Sycophancy in Language Models

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    paper_authors
    Printed name
    Amanda Askell
    Author position
    5
    Identity state
    provisional
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 142 pith inbound references from cited_work_pith_inbound_counts
  5. 2023 Pith paper

    Towards Measuring the Representation of Subjective Global Opinions in Language Models

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    5
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 39 pith inbound references from cited_work_pith_inbound_counts
  6. 2023 Pith paper

    The Capacity for Moral Self-Correction in Large Language Models

    cs.CL provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    2
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 15 pith inbound references from cited_work_pith_inbound_counts
  7. 2022 Pith paper

    Discovering Language Model Behaviors with Model-Written Evaluations

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    57
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 44 pith inbound references from cited_work_pith_inbound_counts
  8. 2022 Pith paper

    Constitutional AI: Harmlessness from AI Feedback

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 531 pith inbound references from cited_work_pith_inbound_counts
  9. 2022 Pith paper

    Measuring Progress on Scalable Oversight for Large Language Models

    cs.HC provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 33 pith inbound references from cited_work_pith_inbound_counts
  10. 2022 Pith paper

    In-context Learning and Induction Heads

    cs.LG provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 145 pith inbound references from cited_work_pith_inbound_counts
  11. 2022 Pith paper

    Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 147 pith inbound references from cited_work_pith_inbound_counts
  12. 2022 Pith paper

    Language Models (Mostly) Know What They Know

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    3
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 323 pith inbound references from cited_work_pith_inbound_counts
  13. 2022 Pith paper

    Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    24
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 118 pith inbound references from cited_work_pith_inbound_counts
  14. 2022 Pith paper

    Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 479 pith inbound references from cited_work_pith_inbound_counts
  15. 2022 Pith paper

    Training language models to follow instructions with human feedback

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    16
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 291 pith inbound references from cited_work_pith_inbound_counts
  16. 2022 Pith paper

    Predictability and Surprise in Large Generative Models

    cs.CY provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 9 pith inbound references from cited_work_pith_inbound_counts
  17. 2021 Pith paper

    A General Language Assistant as a Laboratory for Alignment

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 136 pith inbound references from cited_work_pith_inbound_counts
  18. 2021 Pith paper

    Learning Transferable Visual Models From Natural Language Supervision

    cs.CV provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    8
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 268 pith inbound references from cited_work_pith_inbound_counts
  19. 2020 Pith paper

    Language Models are Few-Shot Learners

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    10
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 408 pith inbound references from cited_work_pith_inbound_counts
  20. 2020 Pith paper

    Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

    cs.CY provisional measured, no current review

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    31
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: no current Pith review exists.
    Citation counts
    • 18 pith inbound references from cited_work_pith_inbound_counts
  21. 2019 Pith paper

    Release Strategies and the Social Impacts of Language Models

    cs.CL provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    4
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 37 pith inbound references from cited_work_pith_inbound_counts
  22. 2019 Pith paper

    The Role of Cooperation in Responsible AI Development

    cs.CY provisional current review present

    paper citation record paper evidence challenge this paper

    Sources and evidence
    Authorship source
    arxiv_oai
    Printed name
    Amanda Askell
    Author position
    1
    Identity state
    provisional
    Source confidence
    0.7
    Review coverage
    Measured: a current Pith review exists.
    Citation counts
    • 3 pith inbound references from cited_work_pith_inbound_counts

Evidence apparatus

The machinery behind this record. Every lane states whether Pith measured it, did not query it, could not reach it, or withheld it.

LaneStateObservedBoundary and source
identity Measured 2 Canonical identity row plus public typed identifiers.
source=authors, author_identifiers
papers Measured 22 of 22 bounded rows Rows attributed to this author UUID in the Pith corpus.
source=paper_authors
works Measured zero 0 of 0 bounded rows Imported works not duplicated by the paper ledger.
source=author_works
reviews Measured 18 of 22 bounded rows Coverage count only. No review outcome is projected onto the person.
source=current_verdicts
citations Measured 22 of 22 bounded rows Counts remain itemized by work and source.
source=cited_works
coauthors Measured 50 of 22 bounded rows Shared-work edges from admitted paper rows.
source=paper_authors
account Unavailable No public count of 1 bounded rows Account metadata is separate from corpus evidence.
source=users.author_id
Public identity sources
  • name variant
    Amanda Askell     backfill
    confidence 0.6

identity history

Enumerated research scope

Fields and dates come only from enumerated, non-disputed Pith paper rows. They do not claim career completeness.

  • cs.CL15 rows
  • cs.CY3 rows
  • cs.CR1 rows
  • cs.CV1 rows
  • cs.HC1 rows
  • cs.LG1 rows
  • 20192 rows
  • 20202 rows
  • 20212 rows
  • 202210 rows
  • 20234 rows
  • 20241 rows
  • 20251 rows
Shared-work index
Record scope

The work queries are bounded. Missing rows may mean measured zero, an unavailable source, a query that did not run, or private data that Pith withheld. The lane table keeps those cases separate.

Paper findings remain attached to papers. They do not become findings about this researcher.