What gives you away: how LLMs form opinions of you

·LessWrong··

LLMs form opinions of the people they are talking to.Chen et al. has shown that probes can extract attributes about the user, such as their age, gender, education, and socioeconomic status. This paper also shows that intervening on these representations can change the LLM's behaviour, proving that it will respond to you differently depending on what it thinks of you. If it thinks you are low socioeconomic status and you ask about travel options, it may filter out more expensive flights - without...

Read full article →

Related Articles

Qwen3.8 27B scores 52 on Artificial Analysis
anana_ · Hacker News · 5h ago
AI-Generated GitHub Copilot “Autofix” Allowed Compromise of Snowflake's Jira
galnagli · Hacker News · 9h ago
India has paved the way for charging merchants a fee on UPI transactions
monkey_monkey · Hacker News · 3h ago
Self hosted email continues to steeply decline
minusf · Hacker News · 12h ago
Apple's App Tracking Transparency treated its own apps better than rivals
nyku · Hacker News · 9h ago