Jasmine Brazilek

Karma: 83

What is the Alignment Community Thinking?

jonahmattwoodward, MilesTS, Jasmine Brazilek and Maheep Chaudhary

6 Sep 2026 16:34 UTC

5 points

0 comments7 min readLW link

Research scientists for CaML: Investigating whether mid-training can survive RL

Jasmine Brazilek1 Sep 2026 18:13 UTC

16 points

2 comments2 min readLW link

Coercion and Deception in AI-to-AI Management

jonahmattwoodward, Jasmine Brazilek, MilesTS and Maheep Chaudhary

10 Aug 2026 16:13 UTC

12 points

0 comments8 min readLW link

(compassionalignedml.substack.com)

Community Polls on Alignment Controversies II

jonahmattwoodward, MilesTS and Jasmine Brazilek

30 Jul 2026 21:05 UTC

9 points

15 comments2 min readLW link

(forum.effectivealtruism.org)

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

jonahmattwoodward, Jasmine Brazilek, Maheep Chaudhary, Oliver Tullio, Joel Christoph and MilesTS

17 Jul 2026 17:28 UTC

13 points

14 comments3 min readLW link

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

Jasmine Brazilek and HoVY

17 Jun 2026 22:48 UTC

2 points

0 comments13 min readLW link

(forum.effectivealtruism.org)

[Linkpost] Community polls on alignment controversies

Jasmine Brazilek, MilesTS and jonahmattwoodward

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)

Jasmine Brazilek and MilesTS

21 May 2026 3:29 UTC

11 points

0 comments6 min readLW link