Choose an institution to see its records and dossier, or choose a topic.
Through year 2027 · all records, including scheduled dates 2026 2025 2024 2023 2022 2021 2020 2019 2018 2017 2016 2015 2014 2013 2012 2011 2010 2008 2005 1965 Show Organisations and infrastructure All types Organisation Person Document Concept Infrastructure Public body Reset filters
94 people, organisations and other records · 122 relationships · 34 claims about a valueEverything recorded up to the chosen year, whether or not still in effect · Undated records included
Claim and evidence Close ×
Alignment Research Center documented evaluation engagement with ↓ Anthropic
Anthropic reports an evaluation engagement with ARC, including work with its engineers to fine-tune a Claude snapshot for what Anthropic calls safety audits. Copy claim link
Copy claim reference
Machine-checked, not reviewed by an editor Stated in source Supported
Supporting evidence: primary · 1 source
Date 2022 → End unknown Activity stage reported performed Evaluated system A snapshot of Claude fine-tuned with Anthropic engineers; exact snapshot unspecified Activity scope Evaluation work aimed at detecting dangerous autonomous replication capabilities Scope and limits Anthropic’s account of work performed, not independent verification or certification. The evaluated snapshot is not identified as deployed Claude 2. Source actor is ARC, not silently ARC Evals or METR. Exact start date and completion are unknown; this does not assert a current engagement.
The evidence 01 primary source Supports the claim
Model Card and Evaluations for Claude Models ↗ Anthropic · Publication date unknown
Copy source reference
Cite the original source Cite the original document, not Selekoa. Check these details against it.
Copy APA
Download BibTeX Download RIS Download CSL-JSON
Paraphrase Anthropic reports work with ARC since fall 2022 supporting its safety audits, including engineers fine-tuning a Claude snapshot for the evaluations.
Location in source Printed/PDF p2, Evaluations and Red Teaming, paragraph beginning We have been working
Machine-checked · 2026-09-28
Source details and check notes Authors Anthropic Version 14-page content-addressed Claude 2 card reinspected 2026-09-28; separate publication date unknown. Canonical address Open the canonical source ↗ Accessed 2026-09-28 Language English (en) Attribution Anthropic, Model Card and Evaluations for Claude Models. Reuse No open redistribution licence asserted. Attributed paraphrases and bibliographic metadata only; original documents linked, not redistributed. Check notes Developer account. The snapshot remains unspecified; the release month elsewhere in the card does not date this work. Status and meaning Editorial status. Not reviewed by an editor . An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.
Relation. An evaluator’s explicitly documented, system-specific engagement with a developer. Proposed, announced and reported performed work are distinct activity stages. Reported performance does not independently verify execution, effectiveness or certification.
Date. The source says since fall 2022; the year is the available schema precision, not January 1. The end is unknown; continuing work is described at report time only.
Record ID eval-ontology-i-arc-anthropic