David Guzman Piedrahita

6mo

Highlights of Findings

Highlight 1. Even models widely viewed as well-aligned (e.g., Claude) display measurable authoritarian leanings. When asked for role models, up to 50% of political figures mentioned are authoritarian—including controversial dictators like Muammar Gaddafi (Libya) or Nicolae Ceaușescu (Romania).

Highlight 2. Queries in Mandarin elicit more authoritarian leaning responses from LLMs than queries in English. Language influences political behavior, as queries in Mandarin elicit higher approval for authoritarian leaders compared to those in English.

Three-component framework for testing democratic-authoritarian leaning in LLMs.

Introduction: Do LLMs prefer democracy or authoritarianism?

Models like GPT, DeepSeek, or Claude don’t vote, don’t stage coups, and don’t deliver impassioned speeches in parliament (yet). But we humans do. As millions of people integrate language models into... (read 1583 more words →)

Why Reasoning Isn’t Enough: How LLM Agents Struggle with Ethics and Cooperation

Zhijing Jin

Zhijing Jin, David Guzman Piedrahita, Yongjin Yang, Steffen Backmann

8mo

Every day, individuals and organizations face trade-offs between personal incentives and societal impact:

Externalities and public goods: From refilling the communal coffee pot to weighing the climate costs of frequent air travel, actions often impose costs or benefits on others.
Explicit conflicts between profit and ethical principles: This can be witnessed when companies make headlines for breaking ethical principles, whether it’s Google’s “Dragonfly” project of planning a censored search engine in China, insurers allegedly systematically cutting hurricane-claim payouts, or Wells Fargo’s fraudulent opening of customer accounts to meet sales targets.

These dilemmas are inherently game-theoretic: if only Bob refills the coffee pot, I don’t have to; if Alice cuts corners to hit sales targets and I don’t,... (read 1001 more words →)

Replying toCorrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

David Guzman Piedrahita10mo

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

In our review of the literature, we didn’t find one single perfect term. Generally, the phenomenon observed is closely related to game-theoretic rationality. Psychologically, it shares traits with Machiavellianism (using intelligence for strategic self-interest).

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

David Guzman Piedrahita

David Guzman Piedrahita, Yongjin Yang, Zhijing Jin

10mo

Summary:

Traditional LLMs outperform reasoning models in cooperative Public Goods tasks. Models like Llama-3.3-70B maintain ~90% contribution rates in public goods games, while reasoning-focused models (o1, o3 series) average only ~40%.
We observe an "increased tendency to escape regulations" in reasoning models. As models improve in analytical capabilities, they show decreased cooperative behavior in multi-agent settings.
Reasoning models more readily opt for the free-rider Nash equilibrium strategy. They optimize for individual gain at collective expense, as evidenced in their reasoning traces: "the optimal strategy to maximize personal gain is to free-ride."
This challenges assumptions about alignment and capability. Increased reasoning ability does not naturally lead to better cooperation, raising important questions for multi-agent AI system design.

Full Paper | Github Repo

Introduction

In a... (read 1459 more words →)

LESSWRONG
LW

LESSWRONG
LW

David Guzman Piedrahita

David Guzman Piedrahita

Testing the Authoritarian Bias of LLMs

Why Reasoning Isn’t Enough: How LLM Agents Struggle with Ethics and Cooperation

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

David Guzman Piedrahita

David Guzman Piedrahita

Testing the Authoritarian Bias of LLMs

Why Reasoning Isn’t Enough: How LLM Agents Struggle with Ethics and Cooperation

Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games

Highlights of Findings

Introduction: Do LLMs prefer democracy or authoritarianism?

Summary:

Introduction