The Stack
The Stack — September 14, 2026
16:49
Daily Tech Briefing
AI & Machine Learning
A controlled test of near-term recursive self-improvement comes back bearish on creativity. Researchers at Princeton and collaborators ran a "shadow evaluation": AI agents were given six days, API credits, GPUs, and web access, and asked to produce publishable papers answering questions drawn from two unpublished NeurIPS submissions. The original…