Trajectory (@trajectorylabs) / X

Trajectory

25 posts

Trajectory

@trajectorylabs

Building the platform for Continual Learning

Joined December 2025

Trajectory reposted
Harvey
@harvey
Jun 10
We partnered with @trajectorylabs to post-train NVIDIA Nemotron 3 Ultra for legal. Here’s what we found: 1) Open-weight models can reach frontier legal performance. On our Legal Agent Benchmark (LAB), Nemotron 3 Ultra started at a 0% all-pass rate. After post-training, it
Trajectory
@trajectorylabs
Jun 10
1/ We post-trained @nvidia Nemotron 3 Ultra on @harvey Legal Agent Bench in under 24 hours. The result: an open model reaching the same band as leading closed models on legal work, at a fraction of the cost. The correlating story: when a new open model ships, Trajectory can
49K
Trajectory
@trajectorylabs
Jun 10
1/ We post-trained @nvidia Nemotron 3 Ultra on @harvey Legal Agent Bench in under 24 hours. The result: an open model reaching the same band as leading closed models on legal work, at a fraction of the cost. The correlating story: when a new open model ships, Trajectory can
78K
Trajectory
@trajectorylabs
Jun 10
Replying to @trajectorylabs
4/ The shift is that the most valuable training signal already lives inside companies. Every brief, edit, correction, review, approval, and workflow is proprietary data that can make their models better. Open models give companies the weights. Trajectory helps them turn their
1.9K
Trajectory
@trajectorylabs
Jun 10
5/ Read the full article here:
Post-Training NVIDIA Nemotron 3 Ultra on Harvey LAB in Under 24 Hours - Trajectory
From trajectory.ai
1.8K
Trajectory reposted
Tinker
@tinkerapi
Jun 4
Nemotron 3 Ultra from @nvidia is out today and available on Tinker day one! The flagship from the Nemotron family is built for long-running agents; @trajectorylabs have been using it in early access to power continual learning workflows.
NVIDIA AI
@NVIDIAAI
Jun 4
Today we're shipping Nemotron 3 Ultra. A 550B MoE frontier-intelligence open model built for long-running agents. It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.
00:00
7.8K
Trajectory reposted
Mercor
@mercor_ai
Jun 3
We worked with @trajectorylabs to run their SDPO++ algorithm on APEX-Agents and see what it could do with real production data. Pass rates went from 5% to 25% on GPT-OSS-120B, and the curve is still climbing. Read more about our work together in their blog post below.
Trajectory
@trajectorylabs
Jun 2
5 Days of Trajectory 🏹Day 5: Scaling SDPO to Agentic Tasks Continual learning means you must train on data from production. But production gives you one example per task. A user makes a request once. You get one trajectory, not a batch. However, current RL algorithms
13K
Trajectory
@trajectorylabs
Jun 2
5 Days of Trajectory 🏹Day 5: Scaling SDPO to Agentic Tasks Continual learning means you must train on data from production. But production gives you one example per task. A user makes a request once. You get one trajectory, not a batch. However, current RL algorithms
40K
Trajectory
@trajectorylabs
Jun 2
See the full deep dive here:
Scaling SDPO - Trajectory
From trajectory.ai
1.9K
Trajectory
@trajectorylabs
Jun 1
🏹 5 Days of Trajectory. Day 4 - Why We’re Building Trajectory AI is the most capable software ever built. You correct it. You teach it what you want. However, the next session starts, and the learning is gone. This is deeply unnatural - nothing intelligent works this
63K
Trajectory
@trajectorylabs
Jun 1
See the full piece here:
Continual Learning: End of Frozen Software - Trajectory
From trajectory.ai
1.5K
Trajectory
@trajectorylabs
May 31
We’re taking a quick break for the 5 days of Trajectory, but wanted to take this time to say that we’ve been named to @Redpoint’s 2026 Infrared 100 as one of the companies shaping the future of AI infrastructure. We're so grateful for the recognition so early in our journey,
7.9K
Trajectory
@trajectorylabs
May 30
🏹5 Days of Trajectory. Day 3 - An Open Source Training Stack for Continual Learning Building the platform for continual learning requires both partnering with pioneering AI companies, as we showed on Day 2 with Harvey, and working toward frontier research, which we are
94K
Trajectory
@trajectorylabs
May 30
Try it out here: Code: github.com/NovaSky-AI/Sky… Getting Started : trajectory.ai/field-notes/mu… (Section Getting-Started)
3.9K
Trajectory
@trajectorylabs
May 30
Read the full post here:
Multi-LoRA Training for Continual Learning - Trajectory
From trajectory.ai
3.3K
Trajectory reposted
NVIDIA AI
@NVIDIAAI
May 29
This is a great read on post-training and open models. @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.
Harvey
@harvey
May 29
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
31K
Trajectory reposted
Harvey
@harvey
May 29
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
Trajectory
@trajectorylabs
May 29
Welcome to Day 2. Yesterday, we showed the broader work we're doing with the pioneers of continual learning. Today we'd like to deep dive on one: how we post-trained an open model for legal work, in partnership with @harvey. We've built a platform where production data is the
60K
Trajectory
@trajectorylabs
May 29
Welcome to Day 2. Yesterday, we showed the broader work we're doing with the pioneers of continual learning. Today we'd like to deep dive on one: how we post-trained an open model for legal work, in partnership with @harvey. We've built a platform where production data is the
66K
Trajectory
@trajectorylabs
May 29
Read the full piece here:
The Sovereign Path for Continual Learning: Early Results on Harvey LAB with NVIDIA Nemotron -...
From trajectory.ai
2.1K