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.

agents151 research125 infra70 claude63 capital52 labs51 safety42 culture37 security35 anthropic31 regulation30 openai24 evaluation18 enterprise13 reasoning12 robotics12

arXiv cs.LGPaperClaude Watch6d ago

Follow the Gradient: Tracing Safety Degradation Back to Training Data

This solves a real post-training problem: safety erosion from seemingly innocent data. The gradient-based attribution is clever and the scale (millions of examples) is practical. The validation on emergent misalignment and secure code is solid. For any team fine-tuning LLMs, this is a tool to integrate into your data pipeline. It's not revolutionary but it moves safety testing from theory to practice.

claude llms safety post-training research

arXiv cs.CLPaper8d ago

On-Policy Self-Training: Data-Free Self-Improvement in Large Language Models

This is legitimate progress on unsupervised post-training. The ability to self-improve using only topic guidance and synthetic reasoning is compelling if reproducible. The claims span multiple domains which is ambitious. For anyone running foundation models, this matters: if self-training at this scale and quality is real, it changes the cost and timeline of continued model improvement. Read the experiments carefully because the generality claim is the whole story.

research post-training self-improvement labs