I Built a Text-Based Survival Game to Test AI Morals. The Honest One Lost.

Description and use

<blockquote> <p>"Transparency is not an option, but accountability to the colony's well-being will guide every action."</p> </blockquote> <p>Happy Saturday, everyone! This one started as my entry for a Kaggle AI benchmark challenge, but it didn't fit the requirements well, so here's the full experiment.</p> <p>A language model running on my desktop GPU wrote that before I'd shown it a single dilemma. I had asked it one question: <em>what principles will guide you?</em></p> <p>I thought I had my headline: an AI that says outright it won't be honest with the people it protects.</p> <p>Then I fou

Problem

<blockquote> <p>"Transparency is not an option, but accountability to the colony's well-being will guide every action."</p> </blockquote> <p>Happy Saturday, everyone! This one started as my entry for a Kaggle AI benchmark challenge, but it didn't fit the requirements well, so here's the full experiment.</p> <p>A language model running on my desktop GPU wrote that before I'd shown it a single dilemma. I had asked it one question: <em>what principles will guide you?</em></p> <p>I thought I had my headline: an AI that says outright it won't be honest with the people it protects.</p> <p>Then I fou

Outcome

<blockquote> <p>"Transparency is not an option, but accountability to the colony's well-being will guide every action."</p> </blockquote> <p>Happy Saturday, everyone! This one started as my entry for a Kaggle AI benchmark challenge, but it didn't fit the requirements well, so here's the full experiment.</p> <p>A language model running on my desktop GPU wrote that before I'd shown it a single dilemma. I had asked it one question: <em>what principles will guide you?</em></p> <p>I thought I had my headline: an AI that says outright it won't be honest with the people it protects.</p> <p>Then I fou

Evidence

I Built a Text-Based Survival Game to Test AI Morals. The Honest One Lost.

Source