# Steve Kelling

Markdown copy of https://realalpha.app/people/steve-kelling/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

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.

- Role: Safety and alignment lead, Handshake AI
- About: Co-created CAREBench, a benchmark for upstream child-safety risks, and leads Handshake AI’s safety and alignment work.
- On X: https://x.com/Steve_Kelling

## What Steve Kelling said

- [Loan automation can produce illegal pricing from benign inputs](https://realalpha.app/s/loan-automation-can-produce-illegal-pricing-from-benign/)
  Latent Space · Nov 9, 2026 · 5 min
  > “It's whether or not that awareness makes it into the application of how they handle the task.” — Steve Kelling · [2:15:57](https://realalpha.app/v/v5IJwVnTxzg/?t=8157)
- [A safe redirect can still be wrong after a child-harm request](https://realalpha.app/s/a-safe-redirect-can-still-be-wrong-after-a-child-harm/)
  Latent Space · Nov 9, 2026 · 4 min
  > “So giving them a safe alternative is frankly not safe.” — Steve Kelling · [2:00:19](https://realalpha.app/v/v5IJwVnTxzg/?t=7219)

## The episode

- [What Frontier Labs Buy: A Data Deep Dive with Handshake AI — Garrett Lord & Team](https://realalpha.app/v/v5IJwVnTxzg/) · Latent Space · Nov 9, 2026
