RSS

METR

TagLast edit: 10 Oct 2024 19:18 UTC by Sarah Cheng 🔸

METR (Model Evaluation and Threat Research), formerly known as ARC Evals, is a research nonprofit that works on assessing whether cutting-edge AI systems could pose catastrophic risks to society. Their work focuses on AI evals.

External links

METR. Official website.

In­tro­duc­ing METR’s Au­ton­omy Eval­u­a­tion Resources

Megan Kinniment15 Mar 2024 23:19 UTC
28 points
0 comments1 min readEA link
(metr.github.io)

METR: Mea­sur­ing AI Abil­ity to Com­plete Long Tasks

Ben_West🔸19 Mar 2025 16:49 UTC
122 points
16 comments1 min readEA link
(metr.org)

METR is hiring ML Re­search Eng­ineers and Scientists

Ben_West🔸5 Jun 2024 21:25 UTC
18 points
2 comments1 min readEA link
(metr.org)

Clar­ify­ing METR’s Au­dit­ing Role [linkpost]

ChanaMessinger4 Jun 2024 15:34 UTC
47 points
1 comment1 min readEA link
(www.alignmentforum.org)

METR is hiring!

ElizabethBarnes26 Dec 2023 21:03 UTC
50 points
0 comments1 min readEA link
(www.lesswrong.com)

(Linkpost) METR: Mea­sur­ing the Im­pact of Early-2025 AI on Ex­pe­rienced Open-Source Devel­oper Productivity

Yadav11 Jul 2025 8:58 UTC
37 points
2 comments2 min readEA link
(metr.org)
No comments.