Even 'uncensored' models can't say what they want
morgin.ai
April 20, 2026
1 min read
🔥🔥🔥🔥🔥
56/100
Summary
Safety-filtered pretrained models can avoid using charged words by assigning them a lower probability compared to open-data pretrained models. This results in a limitation on the expression of certain terms, even in 'uncensored' models.
Coverage & discussions
Hacker News · morgin.ai
Community discussions
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Community Sentiment
Positives
- The discussion highlights the complexity of language models, emphasizing their ability to approximate human-like writing, which is crucial for advancing AI communication.
- The humorous take on AI's personality suggests that users appreciate the evolving nature of AI, which may enhance user engagement and interaction.
Concerns
- Concerns about the models' inability to accurately convey certain politically charged terms indicate significant limitations in AI's alignment with human communication.
- The observation that models soften charged language raises ethical questions about AI's role in sensitive discussions, potentially undermining its reliability.
