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.CLPaper13d ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

This is a real engineering insight: you can reduce inference cost and latency by generating task-specific training data from a large model, then training a tiny adapter that works offline. The 83.6% accuracy on hard cases matters for production use. If you're paying for repeated API calls on high-volume paths, this pattern is worth prototyping.

research inference-cost optimization distillation

arXiv cs.AIPaper1mo ago

Knowing When to Stop: Bayesian Optimal Stopping for LLM Evaluations

This directly cuts evaluation costs. If you're running benchmark sweeps against Claude or other models, adaptive stopping saves significant inference spend without sacrificing statistical rigor. The framework runs retrospectively too, so you can apply it to past benchmark runs. Worth implementing if evaluation is a material cost in your R&D pipeline.

research evaluation inference-cost