RSS

Teun van der Weij

Karma: 196

How to miti­gate sandbagging

Teun van der Weij23 Mar 2025 17:19 UTC
3 points
0 comments8 min readEA link

The Elic­i­ta­tion Game: Eval­u­at­ing ca­pa­bil­ity elic­i­ta­tion techniques

Teun van der Weij27 Feb 2025 20:33 UTC
3 points
0 comments2 min readEA link

[Paper] AI Sand­bag­ging: Lan­guage Models can Strate­gi­cally Un­der­perform on Evaluations

Teun van der Weij13 Jun 2024 10:04 UTC
24 points
2 comments2 min readEA link
(arxiv.org)

List of pro­jects that seem im­pact­ful for AI Governance

JaimeRV14 Jan 2024 16:52 UTC
40 points
2 comments13 min readEA link

Beyond Hu­mans: Why All Sen­tient Be­ings Mat­ter in Ex­is­ten­tial Risk

Teun van der Weij31 May 2023 21:21 UTC
12 points
0 comments13 min readEA link

An­nounc­ing the Euro­pean Net­work for AI Safety (ENAIS)

Esben Kran22 Mar 2023 17:57 UTC
124 points
3 comments3 min readEA link

Teun_Van_Der_Weij’s Quick takes

Teun van der Weij23 Jun 2022 1:52 UTC
1 point
1 commentEA link