Google DeepMind's Logan Kilpatrick: Why the Model Eats the Harness
Training Data
Jun 11
Google DeepMind's Logan Kilpatrick: Why the Model Eats the Harness
Google DeepMind's Logan Kilpatrick: Why the Model Eats the Harness

Training Data
Jun 11
Unprocessed episode, you can be the first!
Shownote
Shownote
The entire startup ecosystem is racing to build agent harnesses. Logan Kilpatrick, who leads Google AI Studio and the Gemini API, argues that scramble has a roughly 12-month shelf life. Models will absorb the scaffolding and run it natively, so the edge mo...
Highlights
Highlights
Chapters
Chapters
Transcript
Transcript
