RSS

Jasmine Brazilek

Karma: 281

compassionml.com

Co­er­cion and De­cep­tion in AI-to-AI Management

Jonah Woodward10 Aug 2026 16:14 UTC
10 points
3 comments8 min readEA link
(compassionalignedml.substack.com)

Com­mu­nity Polls on Align­ment Con­tro­ver­sies II

Jasmine Brazilek30 Jul 2026 20:25 UTC
30 points
168 comments2 min readEA link

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

Jonah Woodward17 Jul 2026 17:05 UTC
45 points
5 comments3 min readEA link

[Question] Com­mu­nity Polls on Align­ment Controversies

Jasmine Brazilek16 Jun 2026 19:44 UTC
70 points
69 comments1 min readEA link

Assert, don’t de­scribe. Lin­guis­tic Fea­tures that shift LLM rea­son­ing about an­i­mal welfare

Jasmine Brazilek5 Jun 2026 15:46 UTC
12 points
0 comments12 min readEA link

Align­ment for An­i­mals

Jasmine Brazilek5 May 2026 16:00 UTC
15 points
0 comments5 min readEA link

Make the fu­ture non-hu­man be­ings de­serve ($5k USD in prizes)

Jasmine Brazilek31 Mar 2026 23:46 UTC
15 points
0 comments3 min readEA link

MORU—A bench­mark for gen­er­al­ized moral compassion

Declan McKenna 🔷10 Mar 2026 15:24 UTC
25 points
0 comments3 min readEA link

An­i­mal Norms In Mo­ral Assess­ment (ANIMA): Eval­u­at­ing LLMs on rea­son­ing about an­i­mal welfare

Sentient Futures5 Nov 2025 1:13 UTC
55 points
7 comments6 min readEA link

AI data gaps could lead to on­go­ing An­i­mal Suffering

Jasmine Brazilek17 Oct 2024 10:52 UTC
14 points
3 comments5 min readEA link

How to boost cre­ative thoughts and pre­vent group­think in your organization

Jasmine Brazilek2 Jul 2022 11:29 UTC
6 points
0 comments2 min readEA link