The principles that guide our discourse and research.
We prioritize asking the hard questions over defending established positions. We explore mechanistic interpretability not just to solve it, but to understand it.
We admit when we are confused. We value truth-seeking over status-seeking. High-trust dialogue requires vulnerability about what we don't know.
We actively bridge the cultural divide. Whether you come from a rationalist blog background or a formal philosophy department, you belong here.
Curiosity means being willing to question everything—including our own assumptions. In our reading groups, we don't just accept conclusions; we probe methodologies, challenge premises, and ask "what if" questions.
We celebrate confusion as the first step toward understanding. If a paper doesn't make sense, that's not a failure—it's an opportunity for deeper inquiry.
We create space for people to say "I don't understand" without judgment. Status games have no place here. A junior researcher's question is as valuable as a senior researcher's insight.
When we're wrong, we update our beliefs publicly. When evidence contradicts our positions, we acknowledge it. This vulnerability builds the trust that makes real progress possible.
AI safety research has historically been siloed between different communities—rationalist bloggers, academic philosophers, industry researchers, and independent thinkers. Each brings unique perspectives.
We actively work to bridge these divides. We translate jargon, we welcome questions, and we make space for diverse approaches to alignment. The next breakthrough could come from anywhere.