The TWIML AI Podcast · Wednesday, September 9, 2026
Chris Potts explains that due to the uncertainty and resource demands of foundational AI research post-GPT-3, his team has shifted focus towards interpretability. This area is seen as relatively inexpensive to pursue and offers a promising path for understanding how complex AI models achieve their capabilities.
“I will say one concrete thing we did was orient a lot of our research toward interpretability.”
“Just the project of understanding how these models end up being so good at such hard tasks.”
“And the reason we did that is it's relatively inexpensive, and it's also an area where clearly you would be explicitly hoping that models would get better because now you have more to explain.”