Pango

Computer use trajectories for better models.

[Chakra Labs @chakra_ai]

Today, we're excited to announce GLADOS-1, the first computer-use (CUA) model post-trained using collective, crowd-sourced trajectories.

Post-trained on UI-TARS-7B-SFT, we improved performance of the base model on OSWorld.

[Pango @trypango]

@orgo 🔥

[Pango @trypango]

Checkout the full map and submit new companies!

https://t.co/tMu9JO3Hm7

[Pango @trypango]

Last week, we published a blog surveying the computer use agent landscape.

Today, we're excited to share our interactive, live market map of the major players in the space.

[Chakra Labs @chakra_ai]

https://t.co/45R51H6Tmf

[Pango @trypango]

Consequently, we're seeing an explosion of companies building critical infrastructure - datasets, environments, developer automation - to help improve the SOTA.

[Chakra Labs @chakra_ai]

https://t.co/45R51H6Tmf

[Pango @trypango]

To get started, all sessions in our HuggingFace datasets now contain links to the action previewer.

better ergonomics = better models = better computer use agents.

https://t.co/jVvMquT1Qx

[Pango @trypango]

The Pango Interactive Actions Previewer is live!

[Pango @trypango]

The Solution
To combat these poor ergonomics, we built the Pango Interactive Actions Previewer, which quickly allows research to view each frame, action, and screenshot combination from (2) for quality.

[Pango @trypango]

feel the agi

(with longitudinal, organic, compensated, system-2 reasoned user sessions)

[Sam Altman @sama]

watching chatgpt agent use a computer to do complex tasks has been a real "feel the agi" moment for me; something about seeing the computer think, plan, and execute hits different.

[Pango @trypango]

@toptickcrypto we are so far from agi

much work to be done

[Pango @trypango]

The Pango dataset is now live on HuggingFace!

This presents the first large-scale dataset of real users performing authentic work tasks in business productivity software.

[Pango @trypango]

What's next?
Scaling to 100,000+ hours through 2025 across more applications to improve the SOTA in computer use.

https://t.co/nhou0DiyVF

[Pango @trypango]

This dataset is perfect for:
- Post-training computer use agents on authentic patterns
- Research on temporal reasoning & error recovery
- Improving existing models with System 2 reasoning behavior

[Pango @trypango]

What makes it unique:
- Real longitudinal work sessions, not scripted demos
- Full interaction traces (clicks, keystrokes, screenshots, video)
- Error recovery patterns that most datasets miss
- Synthetically generated thought metadata for training reasoning models