Your hub for Alignment news and research — curated daily from 50 top AI sources including OpenAI, Anthropic, Google DeepMind, and more. Every article is reviewed and enriched with editorial analysis by the DeepTrendLab team.
Fictional portrayals of artificial intelligence can have a real effect on AI models, according to Anthropic.
Current critic-less RLHF methods aggregate multi-objective rewards via an arithmetic mean, leaving them vulnerable to constraint neglect: high-magnitude success in one objective can numerically offset critical failures in others (e.g.,…
In this post, we take a deeper look at how RLAIF or RL with LLM-as-a-judge works with Amazon Nova models effectively.
This is a writeup based on a lightning talk I gave at an InkHaven hosted by Georgia Ray, where we were supposed to read a paper in about an hour,…
ControlAI's mission is to avert the extinction risks posed by superintelligent AI. We believe that in order to do this, we must secure an international prohibition on its development. We're…
Training-based control studies how effective different training methods are at constraining the behavior of misaligned AI models. A central example of a case where we want to control AI models…
Code: github.com/ElleNajt/controllability tldr: Yueh-Han et al. (2026) showed that models have a harder time making their chain of thought follow user instruction compared to controlling their response (the non-thinking, user-facing…
Sometimes people make various suggestions that we should simply build "safe" artificial Superintelligence (ASI), rather than the presumably "unsafe" kind. [1] There are various flavors of “safe” people suggest. Sometimes…
Many people—especially AI company employees [1] —believe current AI systems are well-aligned in the sense of genuinely trying to do what they're supposed to do (e.g., following their spec or…
In this post, I'll go through some of my best guesses for the current situation in AI as of the start of April 2026. You can think of this as…