Content Deep Dive

Extending Nemotron 3.5 Super 120B VL with Agentic Web Development Capabilities

Blog post from Hugging Face

Post Details
Company
Date Published
Author
Henrik Klagges, Thomas Endres, Robert Dahlke, Fabian Klemm, Andreas Rabenstein, and Lars Reimann
Word Count
2,184
Company Posts That Month
99
Language
-
Hacker News Points
-
Post removed?
No
Summary

TNG Technology Consulting reports an early-access experiment extending NVIDIA’s open-weight Nemotron 3.5 Super 120B VL model for agentic web development, using reinforcement learning to improve its ability to recreate webpage screenshots as React applications. The work used the DesignBench benchmark’s React generation tasks, refined the project setup and prompts to reduce non-model-related errors, and trained the model through multiple sandboxed OpenCode v2 agent rollouts scored by rendered-image similarity, including CLIP-based measures. Built with NVIDIA NeMo-RL, NeMo-Gym, Megatron, vLLM, Docker, Playwright MCP, and LoRA adapters, the training ran for 128 GPU hours across two NVIDIA B300 nodes. On a held-out evaluation set and a 65,000-token context limit, the fine-tuned model scored 85%, compared with 75% for the base model at the same limit and 83% for the base model with a 262,000-token context, suggesting that targeted RL post-training improved both visual fidelity and token efficiency.

Trends Found in this Post
Trend Post Mentions Total Month Mentions Posts Companies MoM
AI Model Fine-tuning 5 868 227 77 +17%
Reinforcement learning 4 162 88 37 -7%
LLM 3 6,578 1,243 236 +9%
MCP 2 11,921 1,232 235 +12%
Vector Search 1 1,978 415 135 +18%
Use This Data

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.