Amex introduces a framework to prevent AI agents from making unauthorized purchases

AI summary

Editorial policy

米American Expressは、AIエージェントがユーザーの承認を得た範囲でのみ購入を実行するよう設計された新フレームワークを導入した。

Key points

•AIエージェントがユーザーの承認を得た範囲でのみ購入を実行するよう設計された新フレームワークを導入した
•AIを活用したショッピングの普及に伴い、高価な過失や紛争を防止することを目的としている
•ユーザーの意図を超えたAIエージェントの自動購入リスクに対処する仕組みである

#AI Agents #Regulation, Ethics & Society #Security & Misuse#American Express

Read the original

Hacker News10/17/2026

Is MCP becoming the common foundation of smart, decentralised search?

The article examines how MCP allows AI assistants to query sources directly rather than a single index, enabling sources to retain their data, licenses, and names, while discussing current gaps.

CodeZine10/17/2026

AWS Agent Registry Supports Custom Metadata for Registry Records

AWS Agent Registry has been updated to support custom metadata for registry records.

TechCrunch10/17/2026

Replit is no longer working with Anthropic, CEO says

Replit CEO and co-founder Amjad Masad stated at TechCrunch Disrupt 2026 that the company is no longer working with Anthropic.

Hacker News10/17/2026

Why harnesses matter for energy (and token) efficiency

Analysis of a month of agent traffic reveals that the harness, not just the model, determines the energy consumption of coding sessions.

The Verge10/17/2026

Tesla driver says he was asleep and using FSD when he crashed into highway patrol cars

The California Highway Patrol warned that Full Self-Driving is not fully autonomous after a Tesla driver admitted to being asleep while using the feature during a crash into patrol cars.