Records / Vendors' stated offerings
Preference Model: what it sells
RL environments. Builds RL environments used to train AI models, with sample tasks in coding, games, math and image classification.
Dated 15 Oct 2026Source checked 15 Oct 2026Quote found on its page again 16 Oct 2026Basis: stated
In the source's own words
“That's why we're building RL environments for training capable, better-aligned superintelligences.”
Where it was read
What it is about
Figures it counts in
It is shown on its own, not counted into a figure.