AISteerability Challenge invites competitors to suppress AI deception
A September 21 post said registration was open for the IBM and Tara Research contest, with cash prizes and infrastructure from NDIF.
TLDR
The Steerability Challenge asks competitors to suppress AI deception rather than detect lies, according to a September 21 post promoting it. The post named IBM and Tara Research, credited NDIF with infrastructure, and advertised open registration and cash prizes. In a follow-up, the same author said NDIF was hiring for one open role, with more openings to come, and invited people interested in AI interpretability and safety to apply.
Steerability Challenge invites competitors to suppress AI deception
A September 21 post said registration was open for the IBM and Tara Research contest, with cash prizes and infrastructure from NDIF.
TLDR
The Steerability Challenge asks competitors to suppress AI deception rather than detect lies, according to a September 21 post promoting it. The post named IBM and Tara Research, credited NDIF with infrastructure, and advertised open registration and cash prizes. In a follow-up, the same author said NDIF was hiring for one open role, with more openings to come, and invited people interested in AI interpretability and safety to apply.