This is a great read on post-training and open models. @harvey & @trajectorylabs post-trained N...
TL;DR · AI Summary
NVIDIA 和 Trajectory Labs 合作，通过 Nemotron 3 Super 模型在法律领域实现主权持续学习，提供可审计权重和清晰溯源。
Key Takeaways
- Nemotron 3 Super 在复杂法律任务中表现出色，初始结果令人印象深刻。
- 开放权重模型提供可审计性、安全性和清晰的溯源能力。
- 持续学习技术使模型能够通过反馈不断改进性能。
Outline
Jump quickly between sections.
- §引言
介绍 NVIDIA 和 Trajectory Labs 的合作背景及目标。
描述 Nemotron 3 Super 在法律任务中的表现和优势。
开放权重模型提供可审计性、安全性和溯源能力。
持续学习通过反馈机制提升模型性能。
Mindmap
See how the topics connect at a glance.
查看大纲文本（无障碍 / 无 JS 友好）
- NVIDIA AI 合作项目
Highlights
Key sentences worth saving and sharing.
Nemotron 3 Super 在复杂法律任务中表现出色，初始结果令人印象深刻。
开放权重模型提供可审计性、安全性和清晰的溯源能力。
持续学习技术使模型能够通过反馈不断改进性能。
@harvey & @trajectorylabs post-trained Nemotron 3 Super on complex legal tasks with some very impressive initial results. All with auditable weights, real security, and clear provenance." / X
Don’t miss what’s happening
This is a great read on post-training and open models.
&
post-trained Nemotron 3 Super on complex legal tasks with some very impressive initial results. All with auditable weights, real security, and clear provenance.
Quote
Harvey
@harvey
7h
We're partnering with @trajectorylabs to bring sovereign continual learning to legal AI with NVIDIA Nemotron models. Continual learning allows agents to improve over time from feedback on their work: every redline refines the next draft. Open-weight models offer full x.com/20054351026340…
