← Front page

The TWIML AI Podcast · Wednesday, September 9, 2026

Interpretability as a Key Research Direction in AI

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.

personChris Potts

The tape

3 quotes
I will say one concrete thing we did was orient a lot of our research toward interpretability.
Chris Potts
Just the project of understanding how these models end up being so good at such hard tasks.
Chris Potts
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.
Chris Potts
Heard on The TWIML AI Podcast — “Do AI Tokenomics Matter More Than Model Benchmarks? with Chris Potts - #776, published Wednesday, September 9, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.06