“But by the same token, we’ve never seen any solid evidence in truly real-world scenarios of deception and power-seeking”
Dario Amodei, Co-founder and CEO, Anthropic · April 2025
Title and organization are as of the date said.
Source
- The Urgency of Interpretability · darioamodei.com (article)
- Archived copy (Wayback Machine)
- Content captured 2026-11-13, SHA-256 e8a3d0f51f59af060a15111039f5dd06db1bbd562b7ccb8a8302b365b66bc4ef
Cite this quote
Amodei, D. (2025, April). The Urgency of Interpretability. darioamodei.com. https://www.darioamodei.com/post/the-urgency-of-interpretability
More from Dario Amodei
“On the other hand, I worry that AI itself is advancing so quickly that we might not have even this much time. As I’ve written elsewhere, we could have AI systems equivalent to a “country of geniuses in a datacenter” as soon as 2026 or 2027. I am very concerned about deploying such systems without a better handle on interpretability.”
Dario Amodei, Co-founder and CEO, Anthropic · April 2025
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
“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
“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