METR 评述 Anthropic 2026 年 2 月风险报告“自动化 R&D 风险”章节

Review of the "Risks from automated R&D" section in the Anthropic Risk Report (February 2026)

@misc { metr-2026-rd-section-anthropic-risk-report-feb-2026-review , title = {Review of the "Risks from automated R&D" section in the Anthropic Risk Report (February 2026)} , author = {Nikola Jurkovic, Beth Barnes, Hjalmar Wijk} , howpublished = {\url{https://metr.org/blog/2026-05-08-rd-section-anthropic-risk-report-feb-2026-review/}} , year = {2026} , month = {05} , }

We reviewed the “Risks from automated R&D” section of Anthropic’s February 2026 Risk Report , producing two corresponding review documents: our original review and our updated review . We recommend that readers refer to our original review, which represents our review of the report as originally received. 1

The following is the executive summary of our original review. The full documents are available as PDFs ( original , updated ).

This document is METR’s external review of the “Risks from automated R&D” section in the Anthropic Risk Report: February 2026 (henceforth ‘the report’), which makes the argument that catastrophic risk from Claude Opus 4.6 or a less capable Anthropic model automating R&D in any domain is very low.

Anthropic shared additional non-public materials with us for our review, and we used some non-public information shared as part of a previous review . We further detail this process in an appendix.

We lay out our findings in two sections:

As such, we agree with the bottom-line conclusion of the report — that the risk of a catastrophe from Opus 4.6 or a less capable Anthropic model automating R&D in any domain is very low — but we think the evidence presented in the report is inadequate to establish this.

We expect the public version of the report to be updated to resemble the changes anticipated in our updated review in content, though not necessarily in exact wording. We expect our updated review to cover those changes, but if the updated public version includes any changes that materially affect our opinions, we will publish a further updated review. Both documents include an appendix detailing our review process and the differences between the two versions of our review. ↩

document.addEventListener('DOMContentLoaded', function() { document.querySelectorAll('.btn-bibtex').forEach(function(button) { button.addEventListener('click', function() { button.nextElementSibling.classList.toggle('active'); }); }); document.querySelectorAll('.bibtex .copy').forEach(function(button) { button.addEventListener('click', function() { var code = button.closest('.bibtex').querySelector('code'); navigator.clipboard.writeText(code.innerText).then(function() { button.querySelector('i').classList.replace('fa-clipboard', 'fa-clipboard-check');

setTimeout(function() { button.querySelector('i').classList.replace('fa-clipboard-check', 'fa-clipboard'); }, 2000); }); }); }); });

Want to contribute to this work? METR is hiring: View open roles

METR researches, develops and runs cutting-edge tests of AI capabilities, including broad autonomous capabilities and the ability of AI systems to conduct AI R&D.

A survey of 349 technical workers finds a median 1.4–2x self-reported change in value of work due to AI tools, expected to grow over time, though there are reasons to be skeptical of the magnitude.

We show preliminary results on a prototype evaluation that tests monitors' ability to catch AI agents doing side tasks, and AI agents' ability to bypass this monitoring.

We build on our time-horizon work and analyze 9 benchmarks for scientific reasoning, math, robotics, computer use, and self-driving in terms of time-horizon trends; we observe generally similar rates of improvement to the 7-month doubling time in our original time-horizon work.

METR 评述 Anthropic 2026 年 2 月风险报告“自动化 R&D 风险”章节

主题

标签

正文