Imagine a world where computers could understand not just what we say, but the moral implications behind our words. Researchers are exploring this very possibility using passive brain-computer interfaces (pBCIs). These pBCIs aim to decode our moral judgments in real-time by analyzing brain activity in response to morally charged text. In a recent pilot study, participants were shown videos on sensitive social justice issues like immigration, racial discrimination, and LGBTQ+ rights, followed by written statements expressing different moral stances on these topics. While the study is in its early stages, the results hint at the potential of AI to understand our moral reactions. The researchers found that while distinguishing between different levels of moral agreement or disagreement proved challenging, the pBCI could effectively differentiate between neutral and morally charged statements. This suggests that our brains react distinctly to moral dilemmas, even if those reactions are complex and subtle. This research has significant implications for the future of human-computer interaction. Imagine LLMs (large language models) that could understand the ethical nuances of their generated text, leading to more human-compatible and responsible AI. While there are challenges to overcome, such as improving the accuracy of single-trial moral judgment detection, this research opens exciting new avenues for developing AI systems that are not only intelligent but also ethically sensitive.