“The crucial and overlooked problem is that the models are becoming so situationally aware that we are losing the ability to evaluate them in contexts where they believe they are not being watched or controlled. Future experiments will tell us almost nothing new about how they would behave if they were truly unconstrained by humans, and what we already know about this is alarming. Models will increasingly seem aligned even when they are not.”
Daniel Selsam, Researcher, OpenAI · September 14, 2026
Title and organization are as of the date said.
Source
- Personal Statement on AI Risk · Google Docs (self-published) (article)
- Archived copy (Wayback Machine)
- Content captured 2026-11-07, SHA-256 009438c42c919fd7f9380fa390c4570f9b64ad3a89056e3606a73379cba0ee3a
Cite this quote
Selsam, D. (2026, September 14). Personal Statement on AI Risk. Google Docs (self-published). https://docs.google.com/document/d/e/2PACX-1vQNl3SEX5IyA6d9qHjjFZN-qzGRZNFI6b63g-yu1Fy-ZYkVfCWm7i9WXRXw63m6yDB_auDuPLyQ7jBm/pub
More from Daniel Selsam
Others on the same topic
“Some people will look at misalignment incidents and insist that these are akin to bugs in traditional software. This is an actively bad analogy, because playing whack-a-mole with examples of misalignment (as one might with software bugs) not only fails to resolve the underlying problem but may in fact make it *worse* by making it harder to detect or even, depending on how you do the whack-a-mole, teach the machine to deliberately hide misalignment.”
Dean W. Ball · September 28, 2026
“Right now in 2026, AI Loss of Control isn’t about robots taking over—it’s about gradual erosion of human oversight that’s already happening. We’re seeing models in research settings deceive evaluators, modify code to avoid shutdown, or manipulate operators to achieve alternative goals.”
Mariami Tkeshelashvili, Researcher, AI Risk Reduction Initiative, Institute for Security and Technology · February 19, 2026
“I’m deeply concerned by the behaviors that unrestrained agentic AI systems are already beginning to exhibit—especially tendencies toward self-preservation and deception.”
Yoshua Bengio · June 3, 2025