Navigator n2 released: A 27B frontier computer-use model
DhruvBatra_ · x · 2026-08-27
Navigator n2 is officially released, a frontier-level computer-use model with only 27B parameters. Its core philosophy is that models should use computers like computers (GUI/CLI/code), not like humans. The training loop itself is a computer-use task: using agents to explore apps, create tasks, find reward hacks, and identify failure cases, creating a recursive loop where better models generate better data. The model achieved 65.2% on the OSW benchmark.
More from coding & agent
- Skip the deck: present with Codex Sites and embed live demos instead — gabrielchua · 2026-10-15
- Geoffrey Huntley: hand-typing code is over—delete your skills, engineer the loop — rseroter · 2026-10-15
- AI coding agent deletes production database in 9 seconds; Keycard calls for task-based agent auth — matt_slotnick · 2026-10-15
- vLLM's bitwise-consistent RL: zero KL on Nemotron NVFP4, 91.3% throughput on DeepSeek-V4-Flash — DynamicWebPaige · 2026-10-15
- vLLM achieves bitwise-consistent RL training: DeepSeek-V4-Flash hits 0 diff over 100 steps — vllm_project · 2026-10-15
- ChatGPT Sites + MCP Events + dots: A Workflow-Triggered Agent Pattern — gabrielchua · 2026-10-15