Skip to content
Trending storyDeveloping

Generalist's GEN-0, GEN-1 and GEN-1.5 robot models: claims and access

2 articles2 sourcessince Oct 23Last article 2h ago ·

Overview

AISummary of 2 articles

Generalist says its GEN-0, GEN-1 and GEN-1.5 robot foundation models can learn a new physical task from a short demonstration, without a dedicated dataset.

The company reports roughly 99% success on selected tasks across these models and is moving toward in-context physical prompting, in which a robot is shown an example and then does the work. The Sequence says it remains an open question whether those company-reported gains hold up across complete, long-horizon jobs in real deployments.

On October 29, 2026, Generalist announced it is expanding access to GEN-1.5 and taking sign-ups through a waitlist. Its post on X links to a playlist of other tasks the models can perform and a blog post about GEN-1.5.

Written by AI from the articles below · updated Oct 29, 10:08 AM ET

Check the sources:

Developments

2 developments

  1. Oct 29, 10:03 AM ET · 1 article
    Generalist expands access to its GEN-1.5 physical-world foundation model via waitlist
    Generalist: Generalist expands access to its GEN-1.5 physical-world foundation model
  2. Oct 23, 7:03 AM ET · 1 article
    Generalist builds robot foundation models GEN-0, GEN-1, and GEN-1.5 for promptable physical tasks
    The Sequence: Generalist's GEN-1.5 pushes robots toward learning tasks from a short demonstration

Article timeline

The articles in this story. Times are ET.

Oct 29
  1. GeneralistOfficial
    Generalist expands access to its GEN-1.5 physical-world foundation model

    AIGeneralist is expanding access to GEN-1.5, its latest foundation model for the physical world, and is taking sign-ups through a waitlist. The post links to a playlist of other tasks its models can perform and a blog post about GEN-1.5.

Oct 23
  1. The SequenceBlog
    Generalist's GEN-1.5 pushes robots toward learning tasks from a short demonstration

    AIGeneralist is building robot foundation models trained on large-scale physical data, so new tasks may need only a short demonstration rather than a dedicated dataset. Across GEN-0, GEN-1, and GEN-1.5, the company reports roughly 99% success on selected tasks and moves toward in-context physical prompting. The source notes that whether these company-reported gains hold up across complete, long-horizon jobs in real deployments remains an open question.

Heat Trend

Current comparable heat
10
Peak comparable heat
10Oct 29, 11:00 AM ET
Change in past 24 hours
–

The trend compares only continuously observed participants, so its scope may be smaller than the current heat total. Hover or tap for hourly heat; use arrow keys with a keyboard.