RSS

Jasmine Brazilek

Karma: 47

Would your AI travel agent book a bul­lfight? Test­ing whether agents con­sider an­i­mal welfare with­out be­ing prompted

17 Jul 2026 17:28 UTC
14 points
14 comments3 min readLW link

Assert, don’t de­scribe: how writ­ing style in train­ing data shapes an AI’s moral stance

17 Jun 2026 22:48 UTC
2 points
0 comments13 min readLW link
(forum.effectivealtruism.org)

[Linkpost] Com­mu­nity polls on al­ign­ment controversies

17 Jun 2026 0:09 UTC
8 points
7 comments1 min readLW link
(forum.effectivealtruism.org)

Doc­u­ment-tun­ing in­stills durable an­i­mal com­pas­sion in LLMs (and gen­er­al­izes to hu­mans)

21 May 2026 3:29 UTC
11 points
0 comments6 min readLW link