
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.
Follow Steve Kelling
We’ll email you each new moment, one email a day at most. Plus the best of every big interview, Wednesday and Saturday.
Check your inbox
We sent a link to your address. Click it to finish signing up. Not there in a minute? Look in spam.
or
It’s free.
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
- 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 - 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
- 2:11:20