This article by Mallika Rao looks at the shift from microservices to agentic AI architectures. Where microservices split up functions, agent systems split up decisions, which brings new challenges for observability, reliability and design.
Former React core team member Rachel Lee Nabors discusses local-first applications. She explains how small language models running on the device can offer private, fast and cheaper alternatives to apps built on cloud-hosted LLMs.
MiniMax has released M3.1 Flash, a mixture-of-experts model with 428 billion parameters, about 23 billion of them active, and a 1M-token context window. API pricing is $0.15 per million input tokens and $0.60 per million output tokens, and the weights are due on October 23.
The EU AI Act is pushing companies to tighten governance of their AI agents. Identity, access control, traceability and human oversight are becoming key to balancing agent autonomy with security.
Tenant requests, repairs, reminders and reports keep property managers buried in preparatory work. This opinion piece argues that AI agents built around an agency's own methods can free up time and improve service.
AI agents are increasingly using Link, Stripe's payment service, to shop on behalf of their users, Upstarts Media reports. Stripe has not disclosed any figures.