Dhruv Batra is co-founder and chief scientist of Yutori and previously led embodied AI at Meta’s FAIR lab. On Chain of Thought he explained why Yutori trains browser agents to use pixels and clicks on websites that may never provide APIs.
AI AgentsOpen Source AIAI HardwareAI Coding
Episodes
In their words
Digital surfaces like the web are going to be shared roadways for a long time to come. Some drivers of action are going to be humans. The web was primarily designed for human consumption. If a machine can perceive pixels and click buttons and do the things and report to you that yes, I'm able to do it. There, that's your API.
Most of the Web Will Never Get APIs for AI Agents | Dhruv Batra, Yutori
Quotes lightly edited to remove filler words.