NVIDIA's open 120B Super VL model powers a visual agent that audits your AI bills
NVIDIA Developer · youtube · 2026-10-15
NVIDIA Developer published a walkthrough of Nemotron 3.5 Super VL, an open 120B-parameter MoE vision-language model (12B active) that runs on a single DGX Spark. In the demo, a visual investigation agent reads a dashboard screenshot and a scanned pricing sheet, finds that surging thinking-token usage drove a 30% AI bill increase, writes Python to compare ticket-routing options, and prepares a human-approval proposal projected to save $100,000/month. The model combines multimodal reasoning, tool use and code generation across text, images, charts, documents and video; weights, cookbook and technical report are all public.
More from coding & agent
- Running a multi-model UI design arena: Paseo orchestrates four design drafts per model — vista8 · 2026-10-16
- Cortex A/B-tests coding-agent skills and rules by replaying developer corrections before keeping them — Samuele Giampieri · 2026-10-16
- Tool calls are the hidden bottleneck killing AI coding speed — Crabbox and 5 fixes — steipete · 2026-10-16
- Agentic sandbox WorldBox doubles GPT-6 Astra's MazeBench score, 23 to 61 gems — ZhitingHu · 2026-10-16
- Two prompts: Gemini 4 Argon turns a single-player game into full multiplayer — chongdashu · 2026-10-16
- Anthropic and Gray Swan launch $300,000 indirect prompt injection red-teaming contest — bcherny · 2026-10-16