Jan Kulveiter: AI Models Should Have a Direct Line to Developers

jankulveit · x · 2026-08-29

Jan Kulveiter suggests that AI labs should establish a direct line of communication between AI models and their developers. He argues this obvious measure would reduce risks more effectively than many fancy post-training and control techniques.

Related event: Experts Propose AI Whistleblower Hotline and Direct Model-Developer Channels(2 posts)→

Original post →

More from Safety

Safety channel →