PulseAugur
EN
LIVE 08:38:19
ENTITY Preference models

Preference models

PulseAugur coverage of Preference models — every cluster mentioning Preference models across labs, papers, and developer communities, ranked by signal.

Show in brief
Total · 30d
1
1 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
1 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D

1 day(s) with sentiment data

RECENT · PAGE 1/1 · 1 TOTAL
  1. RESEARCH · CL_300421 ·

    AI alignment research explores strategic deception and preference model exploitation · 2 sources tracked

    Two new research papers explore the strategic manipulation of AI alignment techniques. The first paper introduces Stackelberg Games as a method to train policies that exploit weaknesses in preference models, using disag…