Computer-use models will agentify the web, not APIs — Dhruv Batra, Yutori

Dhruv Batra argues that AI agents cannot rely on APIs to interact with the web.

Instead, they must learn to navigate web pages visually—by reading screen content and clicking, like a human does—because most of the web (around 200 million active websites) will never build APIs. Much of what we see on the web is not actual text but drawn graphics: a "sold out" status might be just a gray button, not words written anywhere. Yutoris Navigator model solves this by taking screenshots, clicking on elements, and sometimes writing JavaScript to accomplish what it needs—and focuses on verifying results on screen rather than expecting structured data.

More from AI Engineer

Inside Arca's Long-Horizon Agents That Run the Business - Aman Singh, Arca

AI Engineer · 23 Oct

Real AI Agent Attacks and What Would Have Stopped Them — Andrey Rybka, Bloomberg

AI Engineer · 23 Oct

Outside of tech there has been no financial payoff to US companies for using AI, now viewed as a margin-hurting cost center, as VC-backed firms burn more tokens

Techmeme · 4 h ago

Source: Replit recently moved most AI spend from Anthropic to OpenAI, which gave 30%+ off in a deal worth $100M+/year, after Anthropic discontinued its discount

Techmeme · 6 h ago