WSJ: “AI Agents Face One Last, Big Obstacle”

From The Wall Street Journal:

An advanced LLM might fail at complex multiplication, for example, while the cheapest, oldest model can ace the test if it has a calculator tool.

But there is another hurdle: Agents will need permission to access apps, APIs and websites if they are ever going to call an Uber or book a flight, the kind of expectation that has been established over the past year.

Humans type passwords or use facial and fingerprint recognition to sign into their accounts, but AI agents require new methods of authorization to address the intermediary role between humans and the services they want to use, according to Alex Salazar, chief executive of startup Arcade.dev.

[Clip]

The effort got a boost last November when Anthropic, the startup behind the chatbot Claude, introduced an open-source standard known as Model Context Protocol. “Just as USB-C provides a standardized way to connect your devices to various peripherals and accessories, MCP provides a standardized way to connect AI models to different data sources and tools,” the user guide says.

Learn More, Read the Complete Article (about 690 words)

Note: An Archived Version of the Article is Available

Filed under: Data Files, News