Preference Model
Reinforcement-learning environments that help AI labs train models to solve tasks without exploiting flaws in the grading system.
$16MSeed
ParticipantJS
Julian Schrittwieser
Activity from announced rounds
Activity in this selectionspice-capital-269395c3
- Rounds participated in
- 2
- Confirmed lead rounds
- 0 1 roles undisclosed
- New companies
- 2 First participation on record · 0 follow-on
- Funding in participating rounds
- $56M 2 disclosed · full round size, not this investor’s share
By stage
By primary sector
By country
Rounds
2 in this selectiondepthfirst
Develops AI-native security platform for software vulnerability detection and fix recommendations
$40MSeries A
Role not disclosed