I asked ChatGPT to explain the image, and it pulled a Westworld “Doesn’t look like anything to me” reply on the “language model hallucinations are lies” box:
This image is a play on the concept of “alignment charts,” which are often used in role-playing games to define character behavior. Here, it classifies different types of lies based on two axes: content (what is being said) and structure (the nature of the lie).
1. **Content purist** vs. **Content rebel**: This axis distinguishes lies based on whether the statement itself is denotatively false (purist) or if any kind of untruthfulness, including misleading but technically true statements, is considered a lie (rebel).
2. **Structure purist** vs. **Structure rebel**: This axis is about the intent and form of the lie. A structure purist requires a conscious intent to deceive, while a structure rebel includes any form of falsehood, whether intentional or not.
The chart then gives examples of lies for each quadrant: - **Content purist / Structure purist**: A classic, intentional lie about a specific fact (“I did not have sexual relations with that woman”). - **Content purist / Structure neutral**: A fantastical lie without a clear intent to deceive (“The Jews are lizard people”). - **Content purist / Structure rebel**: This category is left blank in the image but would include any intentional lie that is factually incorrect. - **Content neutral / Structure purist**: A polite lie with intent to deceive but not about a factual matter (“Oh, thank you so much; you shouldn’t have”). - **Content neutral / Structure neutral**: A procrastinating lie (“I’ll get to it tomorrow”). - **Content neutral / Structure rebel**: Lies that occur due to language misunderstandings or miscommunications (“false cognates are lying”). - **Content rebel / Structure purist**: This category is left blank in the image but would include lies that are misleading in any way with intent to deceive. - **Content rebel / Structure neutral**: Lies that result from errors in reasoning or belief, not language (“Batesian mimicry is lying”). - **Content rebel / Structure rebel**: Lies that are not due to intentional deceit or language issues, but other causes, like a broken clock being incorrect about the time.
The chart is a humorous attempt to categorize lies in a way that mirrors the alignment charts used in gaming, highlighting the complexity and variety of what we consider to be “lies.”
I asked ChatGPT to explain the image, and it pulled a Westworld “Doesn’t look like anything to me” reply on the “language model hallucinations are lies” box:
This image is a play on the concept of “alignment charts,” which are often used in role-playing games to define character behavior. Here, it classifies different types of lies based on two axes: content (what is being said) and structure (the nature of the lie).
1. **Content purist** vs. **Content rebel**: This axis distinguishes lies based on whether the statement itself is denotatively false (purist) or if any kind of untruthfulness, including misleading but technically true statements, is considered a lie (rebel).
2. **Structure purist** vs. **Structure rebel**: This axis is about the intent and form of the lie. A structure purist requires a conscious intent to deceive, while a structure rebel includes any form of falsehood, whether intentional or not.
The chart then gives examples of lies for each quadrant:
- **Content purist / Structure purist**: A classic, intentional lie about a specific fact (“I did not have sexual relations with that woman”).
- **Content purist / Structure neutral**: A fantastical lie without a clear intent to deceive (“The Jews are lizard people”).
- **Content purist / Structure rebel**: This category is left blank in the image but would include any intentional lie that is factually incorrect.
- **Content neutral / Structure purist**: A polite lie with intent to deceive but not about a factual matter (“Oh, thank you so much; you shouldn’t have”).
- **Content neutral / Structure neutral**: A procrastinating lie (“I’ll get to it tomorrow”).
- **Content neutral / Structure rebel**: Lies that occur due to language misunderstandings or miscommunications (“false cognates are lying”).
- **Content rebel / Structure purist**: This category is left blank in the image but would include lies that are misleading in any way with intent to deceive.
- **Content rebel / Structure neutral**: Lies that result from errors in reasoning or belief, not language (“Batesian mimicry is lying”).
- **Content rebel / Structure rebel**: Lies that are not due to intentional deceit or language issues, but other causes, like a broken clock being incorrect about the time.
The chart is a humorous attempt to categorize lies in a way that mirrors the alignment charts used in gaming, highlighting the complexity and variety of what we consider to be “lies.”