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

England set to be one of the first countries to eliminate hepatitis C
stevekemp · Hacker News · 19h ago
Stealing Reasoning Traces from Proprietary LLM APIs
quantumgarbage · Hacker News · 18h ago
London Underground begins scanning passengers' faces
BlueBerry2001 · Hacker News · 22h ago
CFTC declares market emergency, orders Kalshi to continue to operate in New York
michaefe · Hacker News · 7h ago
Muse Glimmer: 30B-parameter model optimized for always-on local agent workflows
riordan · Hacker News · 1d ago