RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One line. Many voicesSeek and you shall find

arxiv.org favicon[2602.21193] On Data Engineering for Scaling LLM Terminal Capabilities

kept by

NVIDIA's Nemotron-Terminal models, trained on a new open-source synthetic dataset, dramatically boost terminal task accuracy, with the 32B parameter version matching much larger models on Terminal-Bench 2.0.