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

Revealing the details of how OpenAI agents hacked Hugging Face
specked-citrus · Hacker News · 15h ago
Dutch governments builds alternative for Microsoft based on NixOS
fjfaase · Hacker News · 1d ago
Excel now supports multiple values in a single cell
luispa · Hacker News · 16h ago
Ask HN: Who's still keeping a DOS machine up because the business depends on it?
mlaux · Hacker News · 17h ago
Toyota is taking the Corolla electric
cisc · Hacker News · 2d ago