Do LLMs Have Desires?

·LessWrong··

Work conducted with Yujun Zhou (yzhou25@nd.edu) and supported by SPARTL;DR:In paired-choice paradigms, LLMs report consistent preferences over outcomes (e.g., types and number of lives saved, types of policies enacted)Some have suggested that this indicates that LLMs have human-like value systemsWe design an experimental framework where LLMs are able to modulate their output quality based on prompt contextWe find that LLMs modulate their output quality in response to effort exhortations, role-pl...

Read full article →

Related Articles

DSpark: Speculative decoding accelerates LLM inference [pdf]
aurenvale · Hacker News · 20h ago
Michigan spent $1.8B and only created 602 jobs
littlexsparkee · Hacker News · 7h ago
Anthropic says Alibaba illicitly extracted Claude AI model capabilities
htrp · Hacker News · 3d ago
How Many Elementary Particles Are There, Really?
rwmj · Hacker News · 16h ago
The gap between open weights LLMs and closed source LLMs
kkm · Hacker News · 1d ago