keivn Posts toward a universal law of AI safety by keivn @ 2026-04-11 | +1 | 0 comments LLM culture shock: a pilot study by keivn @ 2026-03-27 | +3 | 0 comments The Paradox of Ineffective Egoism in Effective Altruism by keivn @ 2025-11-01 | +4 | 0 comments The Will to Create the Future, Not Just Predict It by keivn @ 2025-10-25 | +2 | 0 comments Reframing Unsafe AI: Evidence of Present-Day Risk by keivn @ 2025-10-17 | –11 | 0 comments Dataset Poisoning and AI Alignment Vulnerabilities by keivn @ 2025-09-26 | +1 | 0 comments