The Signal

Everything that matters in AI, with our take.

Updated through the day. Every headline links straight to the source. The two lines underneath are ours.

research1156 agents716 infra561 labs317 culture268 capital253 regulation233 claude175 openai149 safety103 security89 evaluation77 reasoning61 alignment52 benchmarks50 interpretability48

arXiv cs.CLPaper7d ago

Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization

Foundation models are genuinely better at content moderation than existing deployments, but the test is narrow: 4,000 Bluesky posts and a single comparison point. The real question for a platform is reliability at scale and false-positive cost. If you're building moderation infrastructure, this signals that VLMs are table stakes now, but you still need to validate on your specific policy portfolio and acceptable error rates.

research moderation vlm

arXiv cs.CLPaper13d ago

Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content Moderation

This is a sharp diagnostic: LLMs can appear to perform well on aggregated benchmarks while systematically failing at fine-grained criterion application. If you are building or evaluating content moderation systems, this is important. The implication is that a single overall score hides dangerous gaps; you need to test each criterion separately. The paper doesn't offer solutions, just exposes the problem.

research safety moderation evaluation