---
title: "METR: Anthropic redacted much of the \"most informative\" evidence from METR's 100-page report, so readers \"must rely on our judgment more than we consider ideal\" (@metr_evals)"
type: signal
url: https://frontiernewswire.com/s/metr-anthropic-redacted-much-of-the-most-informative-evidence-from-db75d970
published: 2026-11-05T21:30:03.000Z
byline: "Source: TECHMEME"
---

# METR: Anthropic redacted much of the "most informative" evidence from METR's 100-page report, so readers "must rely on our judgment more than we consider ideal" (@metr\_evals)

Source: TECHMEME · Published 2026-11-05 · Canonical: https://frontiernewswire.com/s/metr-anthropic-redacted-much-of-the-most-informative-evidence-from-db75d970

@metr\_evals : METR: Anthropic redacted much of the "most informative" evidence from METR's 100-page report, so readers "must rely on our judgment more than we consider ideal" — We submitted a \~100-page full report on our assessment to Anthropic. For the public version, Anthropic redacted a majority of the evidence we found most informative. As a consequence, the public must rely on our judgment more than we consider ideal.

In this story: [Anthropic](https://frontiernewswire.com/companies/anthropic), [METR](https://frontiernewswire.com/companies/metr), [AI Safety](https://frontiernewswire.com/topics/ai-safety)

## Sources

- [Read the original at TECHMEME](https://www.techmeme.com/261105/p52#a261105p52)

## Related on Frontier

- [Review of the "Risks from automated R\&D" section in Anthropic's Risk Report (August 2026)](https://frontiernewswire.com/s/review-of-the-risks-from-automated-r-d-section-in-anthropics-risk-b51534d8)
- [Independent Assessment of AI R\&D Acceleration at Anthropic in October 2026](https://frontiernewswire.com/s/independent-assessment-of-ai-r-d-acceleration-at-anthropic-in-october-c0effec9)
- [METR: Anthropic's models are improving about twice as fast as they did between March 2024 and October 2025, with internal AI use driving \~80% of acceleration (Tiffany Li/The Information)](https://frontiernewswire.com/s/metr-anthropics-models-are-improving-about-twice-as-fast-as-they-did-7d804aea)
- [How OpenAI, Anthropic, and others are trying to prevent anyone from using their AI tools to disrupt the US midterms, including Anthropic's first-ever "war room" (Steven Lee Myers/New York Times)](https://frontiernewswire.com/s/how-openai-anthropic-and-others-are-trying-to-prevent-anyone-from-71d099ca)
- [Anthropic launches Personal Finance in Claude, letting users connect bank and credit card accounts via Plaid with read-only access to analyze spending trends (Radhika Rajkumar/ZDNET)](https://frontiernewswire.com/s/anthropic-launches-personal-finance-in-claude-letting-users-connect-726c606e)

---

[More Latest Signal](https://frontiernewswire.com/) · [Signals](https://frontiernewswire.com/verified-reporting)