Hugging Face's logo

VANTA Research
https://vantaresearch.xyz
vanta_research
vanta-research
Activity Feed

AI & ML interests

AI for humans.

Recent Activity

unmodeled-tyler  updated a Space 2 days ago
vanta-research/README
unmodeled-tyler  updated a model 3 days ago
vanta-research/atom-olmo3-7b
unmodeled-tyler  updated a model 3 days ago
vanta-research/atom-v1-preview-8b
View all activity

unmodeled-tyler 
posted an update about 21 hours ago
view post
Post
128
Mistral Vibe is awesome!

I've been playing around with it a bit today, and have really been enjoying myself. I'm somewhat picky with CLI tools, so design is important to me. I think Mistral nailed it there. It's easy, clean, intuitive, and Mistral provides free API access to their devstral models to get started which is great.

Yesterday I built an interactive model selector for ollama in Aider. I decided to also configure one for Vibe because simple, clean integrations make my brain happy.

I've included a screenshot below of Mistral Vibe running GLM-4.6 through Ollama Cloud and the model selector!
unmodeled-tyler 
updated a Space 2 days ago
unmodeled-tyler 
updated 9 models 3 days ago
unmodeled-tyler 
posted an update 4 days ago
view post
Post
194
Hey Everyone!

I stumbled across a pretty interesting paper recently and just wanted to share it with you all.

It attempts to quantify a framework for effective human-AI synergy and to answer the question about why some users just seem to be naturally adept at working with AI in collaborative contexts.

From the Abstract,"We demonstrate that collaboration ability is distinct from individual problem-solving ability. Users better able to infer and adapt to others’ perspectives achieve superior collaborative performance with AI–but not when working alone."

This infers that strong collaborative traits between human and AI systems resemble effective collaborative traits between humans. The ability to be an effective problem-solver does not immediately translate to being an effective collaborator or vice versa.

Pretty interesting read, and there's a lot to unpack. Link below if you want to take a look!

https://openreview.net/forum?id=Yhqa8Ljzrj
unmodeled-tyler 
updated a model 5 days ago
unmodeled-tyler 
updated a dataset 8 days ago
unmodeled-tyler 
updated 2 collections 8 days ago
unmodeled-tyler 
updated 3 datasets 8 days ago
unmodeled-tyler 
posted an update 8 days ago
view post
Post
163
NEW DATASET: vanta-research/orbital-mechanics-1

We are excited to release our Orbital-Mechanics-1 dataset! This file includes 3.16k rows of collaborative, conversational, examples in orbital mechanics surrounding:
- Orbital Maneuvers
- Perturbations and Non-Keplerian Effects
- Specialized Orbits
- Multi-Body Dynamics
- Mission Design
- Exoplanet Applications

This dataset was synthetically generated from a subset of high quality, curated examples. After generation all data is initially filtered by a critic agent for quality, and then again filtered after that by a human before making it into the final dataset.

Orbital-Mechanics-1 is designed with the following approach:
- Conceptual Shortcuts: Distilling complex ideas into memorable comparisons
- Physical Intuition: Explaining the "why" behind mathematical formulas
- Limiting Cases: Sanity-checking equations with extreme scenarios
- Practical Context: Connecting theory to real missions and observations
- Step-by-step Reasoning: Building complex concepts from first principles.

Mathematical content is formatted using LaTeX notation for clarity and precision.