Real Alpha
Try Pro free

Guest

Steve Kelling

Safety and alignment lead, Handshake AI

Co-created CAREBench, a benchmark for upstream child-safety risks, and leads Handshake AI’s safety and alignment work.

Real Alpha has cut 2 moments of Steve Kelling (Safety and alignment lead, Handshake AI) talking, from an interview on Latent Space published Nov 9, 2026.

What Steve Kelling said

    1. 2:11:20

      Loan automation can produce illegal pricing from benign inputs

      “It's whether or not that awareness makes it into the application of how they handle the task.”
      at 2:15:57
    2. 1:56:45

      A safe redirect can still be wrong after a child-harm request

      “So giving them a safe alternative is frankly not safe.”
      at 2:00:19

Is this you? Add the badge to your site.

It links to this page, where people can watch every moment we cut from your interviews. It fits a personal site, a link-in-bio page or a press page.

Featured on Real Alpha
PNG

Wrong title or photo? Tell us and we'll fix it